Head-to-head comparison
DeepSeek-V4-Flash vs. GLM-5.2
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
61
shared result series
2
distinct benchmarks
2026-08-16
latest retrieval
Change model selection
Specifications and cost
General specifications and standard API pricing
Undisclosed parameter counts and knowledge cutoffs stay marked as unavailable. The table shows direct standard token pricing, including documented context tiers. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
| Attribute | DeepSeek-V4-Flash | GLM-5.2 |
|---|---|---|
| Provider | DeepSeek | Z.ai |
| Released | Apr 24, 2026 | Jun 16, 2026 |
| Availability | Preview | Open Source |
| Model type | Open Weights | Open Weights |
| Parameters | 284B, 13B active | 744B, 40B active |
| Architecture | Mixture of Experts | Mixture of Experts |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Knowledge cutoff | Not published | Not published |
| Technical sources | Model | Model, Context |
| API pricing per 1M tokens | ||
| API input | $0.14 | $1.4 |
| API output | $0.28 | $4.4 |
| Cache read | $0. | $0.26 |
| Cache write (5 min.) | Not listed | Not listed |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 07/30/2026Source | 07/30/2026Source |
DeepSeek-V4-FlashGLM-5.2
API inputUSD per 1M tokens, base tier
DeepSeek-V4-Flash$0.14Lower price
GLM-5.2$1.4
API outputUSD per 1M tokens, base tier
DeepSeek-V4-Flash$0.28Lower price
GLM-5.2$4.4
Cache readUSD per 1M tokens, base tier
DeepSeek-V4-Flash$0.003Lower price
GLM-5.2$0.26
Performance
Shared benchmarks
Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.
61 shared result series
DeepSeek-V4-FlashGLM-5.2
Arena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,435.476 arena points
GLM-5.21,470.655 arena pointsHigher measured value
CyberBenchOverall. Higher is better. No documented setup difference
DeepSeek-V4-Flash66.716 %
GLM-5.277.359 %Winner
Arena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,438.304 arena points
GLM-5.21,470.655 arena pointsHigher measured value
CyberBenchPatch. Higher is better. No documented setup difference
DeepSeek-V4-Flash72.414 %
GLM-5.281.034 %Winner
Arena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,437.217 arena points
GLM-5.21,459.883 arena pointsHigher measured value
CyberBenchPoC. Higher is better. No documented setup difference
DeepSeek-V4-Flash61.017 %
GLM-5.273.684 %Winner
Arena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,435.23 arena points
GLM-5.21,459.883 arena pointsHigher measured value
Arena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,474.544 arena points
GLM-5.21,521.061 arena pointsHigher measured value
Arena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,481.177 arena points
GLM-5.21,521.061 arena pointsHigher measured value
Arena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,483.133 arena points
GLM-5.21,506.101 arena pointsHigher measured value
Arena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,479.521 arena points
GLM-5.21,506.101 arena pointsHigher measured value
Arena Text, Style ControlCreative writing. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,407.934 arena points
GLM-5.21,449.311 arena pointsHigher measured value
| Benchmark and task | DeepSeek-V4-Flash | GLM-5.2 | Comparability | Source |
|---|---|---|---|---|
| Arena Text, Style ControlOverall | 1,435.476 arena points 95% confidence interval: ±4.153The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,470.655 arena pointsHigher measured value 95% confidence interval: ±5.045The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:overallTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 49,096 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 26,867 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| CyberBenchOverall | 66.716 % | 77.359 %Winner | 1accuracyHigher is betterCohort: vals-cyberbench:1:overallNo documented setup differenceWinner: GLM-5.2DeepSeek-V4-Flash: No further settings disclosed GLM-5.2: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-03Import ID: vals-cyber-2026-08-16-702acaee9aa9Retrieved 2026-08-16 |
| Arena Text, Style ControlOverall | 1,438.304 arena points 95% confidence interval: ±4.22The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,470.655 arena pointsHigher measured value 95% confidence interval: ±5.045The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:overallTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 48,789 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 26,867 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| CyberBenchPatch | 72.414 % | 81.034 %Winner | 1accuracyHigher is betterCohort: vals-cyberbench:1:patchNo documented setup differenceWinner: GLM-5.2DeepSeek-V4-Flash: No further settings disclosed GLM-5.2: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-03Import ID: vals-cyber-2026-08-11-1f20498a3dc1Retrieved 2026-08-11 |
| Arena Text, Style ControlBusiness, management and finance | 1,437.217 arena points 95% confidence interval: ±7.157The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,459.883 arena pointsHigher measured value 95% confidence interval: ±8.752The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_business_and_management_and_financial_operationsTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 9,916 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 5,374 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| CyberBenchPoC | 61.017 % | 73.684 %Winner | 1accuracyHigher is betterCohort: vals-cyberbench:1:pocNo documented setup differenceWinner: GLM-5.2DeepSeek-V4-Flash: No further settings disclosed GLM-5.2: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-03Import ID: vals-cyber-2026-08-11-1f20498a3dc1Retrieved 2026-08-11 |
| Arena Text, Style ControlBusiness, management and finance | 1,435.23 arena points 95% confidence interval: ±7.178The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,459.883 arena pointsHigher measured value 95% confidence interval: ±8.752The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_business_and_management_and_financial_operationsTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 10,055 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 5,374 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlChinese | 1,474.544 arena points 95% confidence interval: ±12.686The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,521.061 arena pointsHigher measured value 95% confidence interval: ±15.24The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:chineseTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,557 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,662 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlChinese | 1,481.177 arena points 95% confidence interval: ±12.66The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,521.061 arena pointsHigher measured value 95% confidence interval: ±15.24The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:chineseTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,529 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,662 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCoding | 1,483.133 arena points 95% confidence interval: ±6.395The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,506.101 arena pointsHigher measured value 95% confidence interval: ±7.714The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:codingTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 14,397 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 7,692 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCoding | 1,479.521 arena points 95% confidence interval: ±6.432The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,506.101 arena pointsHigher measured value 95% confidence interval: ±7.714The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:codingTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 14,353 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 7,692 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCreative writing | 1,407.934 arena points 95% confidence interval: ±7.787The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,449.311 arena pointsHigher measured value 95% confidence interval: ±9.401The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:creative_writingTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 7,974 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 4,900 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCreative writing | 1,408.648 arena points 95% confidence interval: ±7.808The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,449.311 arena pointsHigher measured value 95% confidence interval: ±9.401The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:creative_writingTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 8,019 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 4,900 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEnglish | 1,445.34 arena points 95% confidence interval: ±5.378The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,479.647 arena pointsHigher measured value 95% confidence interval: ±6.503The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:englishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,994 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 11,738 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEnglish | 1,450.015 arena points 95% confidence interval: ±5.421The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,479.647 arena pointsHigher measured value 95% confidence interval: ±6.503The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:englishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,774 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 11,738 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEntertainment, sports and media | 1,405.522 arena points 95% confidence interval: ±7.152The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,441.31 arena pointsHigher measured value 95% confidence interval: ±8.397The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_entertainment_and_sports_and_mediaTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 10,453 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,343 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEntertainment, sports and media | 1,405.113 arena points 95% confidence interval: ±7.086The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,441.31 arena pointsHigher measured value 95% confidence interval: ±8.397The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_entertainment_and_sports_and_mediaTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 10,654 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,343 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExcluding ties | 1,430.81 arena points 95% confidence interval: ±5.433The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,478.207 arena pointsHigher measured value 95% confidence interval: ±6.648The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:exclude_tiesTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 37,067 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 19,914 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExcluding ties | 1,435.522 arena points 95% confidence interval: ±5.476The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,478.207 arena pointsHigher measured value 95% confidence interval: ±6.648The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:exclude_tiesTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 37,085 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 19,914 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExpert prompts | 1,458.397 arena points 95% confidence interval: ±9.185The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,487.47 arena pointsHigher measured value 95% confidence interval: ±11.455The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:expertTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 4,926 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,909 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExpert prompts | 1,467.529 arena points 95% confidence interval: ±9.251The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,487.47 arena pointsHigher measured value 95% confidence interval: ±11.455The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:expertTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 4,924 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,909 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlFrench | 1,445.102 arena points 95% confidence interval: ±15.765The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,489.403 arena pointsHigher measured value 95% confidence interval: ±20.303The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:frenchTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,916 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 992 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlFrench | 1,458.295 arena points 95% confidence interval: ±15.946The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,489.403 arena pointsHigher measured value 95% confidence interval: ±20.303The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:frenchTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,884 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 992 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlGerman | 1,423.659 arena points 95% confidence interval: ±21.582The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,471.871 arena pointsHigher measured value 95% confidence interval: ±27.579The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:germanTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 833 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 473 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlGerman | 1,435.281 arena points 95% confidence interval: ±21.205The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,471.871 arena pointsHigher measured value 95% confidence interval: ±27.579The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:germanTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 872 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 473 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts | 1,459.153 arena points 95% confidence interval: ±4.892The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,488.252 arena pointsHigher measured value 95% confidence interval: ±5.839The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:hard_promptsTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 32,675 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 17,841 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts | 1,458.18 arena points 95% confidence interval: ±4.95The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,488.252 arena pointsHigher measured value 95% confidence interval: ±5.839The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:hard_promptsTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 32,535 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 17,841 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts, English | 1,464.017 arena points 95% confidence interval: ±6.178The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,491.588 arena pointsHigher measured value 95% confidence interval: ±7.548The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:hard_prompts_englishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 15,382 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 7,982 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts, English | 1,464.963 arena points 95% confidence interval: ±6.257The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,491.588 arena pointsHigher measured value 95% confidence interval: ±7.548The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:hard_prompts_englishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 15,145 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 7,982 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlInstruction following | 1,428.017 arena points 95% confidence interval: ±5.969The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,464.375 arena pointsHigher measured value 95% confidence interval: ±7.12The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:instruction_followingTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 16,832 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 9,386 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlInstruction following | 1,434.165 arena points 95% confidence interval: ±6.039The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,464.375 arena pointsHigher measured value 95% confidence interval: ±7.12The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:instruction_followingTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 16,841 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 9,386 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlJapanese | 1,396.126 arena points 95% confidence interval: ±25.789The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,456.909 arena pointsHigher measured value 95% confidence interval: ±31.804The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:japaneseTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 628 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 374 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlJapanese | 1,418.789 arena points 95% confidence interval: ±26.437The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,456.909 arena pointsHigher measured value 95% confidence interval: ±31.804The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:japaneseTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 595 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 374 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlKorean | 1,393.857 arena points 95% confidence interval: ±21.517The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,437.732 arena pointsHigher measured value 95% confidence interval: ±26.273The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:koreanTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 869 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 536 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlKorean | 1,375.542 arena points 95% confidence interval: ±21.534The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,437.732 arena pointsHigher measured value 95% confidence interval: ±26.273The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:koreanTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 919 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 536 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLegal and government | 1,448.527 arena points 95% confidence interval: ±10.217The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,480.83 arena pointsHigher measured value 95% confidence interval: ±13.159The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_legal_and_governmentTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,907 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,183 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLegal and government | 1,458.238 arena points 95% confidence interval: ±10.278The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,480.83 arena pointsHigher measured value 95% confidence interval: ±13.159The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_legal_and_governmentTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,876 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,183 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLife, physical and social science | 1,458.241 arena points 95% confidence interval: ±7.633The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,493.732 arena pointsHigher measured value 95% confidence interval: ±9.3The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_life_and_physical_and_social_scienceTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 7,812 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 4,448 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLife, physical and social science | 1,461.582 arena points 95% confidence interval: ±7.609The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,493.732 arena pointsHigher measured value 95% confidence interval: ±9.3The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_life_and_physical_and_social_scienceTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 7,985 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 4,448 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLonger queries | 1,448.126 arena points 95% confidence interval: ±5.746The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,479.131 arena pointsHigher measured value 95% confidence interval: ±6.674The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:longer_queryTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,643 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 12,386 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLonger queries | 1,449.175 arena points 95% confidence interval: ±5.755The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,479.131 arena pointsHigher measured value 95% confidence interval: ±6.674The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:longer_queryTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,682 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 12,386 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMath | 1,425.263 arena points 95% confidence interval: ±12.232The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,474.32 arena pointsHigher measured value 95% confidence interval: ±16.372The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:mathTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,516 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,276 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMath | 1,440.663 arena points 95% confidence interval: ±12.368The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,474.32 arena pointsHigher measured value 95% confidence interval: ±16.372The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:mathTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,448 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,276 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMathematical professions | 1,431.855 arena points 95% confidence interval: ±11.996The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,486.076 arena pointsHigher measured value 95% confidence interval: ±15.567The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_mathematicalTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,738 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,482 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMathematical professions | 1,441.422 arena points 95% confidence interval: ±12.404The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,486.076 arena pointsHigher measured value 95% confidence interval: ±15.567The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_mathematicalTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,588 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,482 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMedicine and healthcare | 1,459.52 arena points 95% confidence interval: ±10.979The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,486.928 arena pointsHigher measured value 95% confidence interval: ±14.057The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_medicine_and_healthcareTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,440 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,969 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMedicine and healthcare | 1,463.011 arena points 95% confidence interval: ±10.889The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,486.928 arena pointsHigher measured value 95% confidence interval: ±14.057The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_medicine_and_healthcareTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,505 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,969 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMulti-turn | 1,452.835 arena points 95% confidence interval: ±7.482The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,468.614 arena pointsHigher measured value 95% confidence interval: ±9.5The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:multi_turnTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 8,848 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 4,469 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMulti-turn | 1,446.059 arena points 95% confidence interval: ±7.528The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,468.614 arena pointsHigher measured value 95% confidence interval: ±9.5The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:multi_turnTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 8,708 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 4,469 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlNon-English | 1,422.787 arena points 95% confidence interval: ±5.078The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,455.529 arena pointsHigher measured value 95% confidence interval: ±6.021The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:non_englishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 27,100 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 15,126 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlNon-English | 1,422.674 arena points 95% confidence interval: ±5.146The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,455.529 arena pointsHigher measured value 95% confidence interval: ±6.021The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:non_englishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 27,013 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 15,126 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlPolish | 1,439.239 arena points 95% confidence interval: ±18.981The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,450.407 arena pointsHigher measured value 95% confidence interval: ±26.447The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:polishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,007 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 479 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlPolish | 1,429.767 arena points 95% confidence interval: ±18.83The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,450.407 arena pointsHigher measured value 95% confidence interval: ±26.447The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:polishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,019 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 479 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlRussian | 1,432.925 arena points 95% confidence interval: ±8.941The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,468.581 arena pointsHigher measured value 95% confidence interval: ±11.762The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:russianTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 5,272 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,693 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlRussian | 1,437.146 arena points 95% confidence interval: ±9.061The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,468.581 arena pointsHigher measured value 95% confidence interval: ±11.762The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:russianTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 5,232 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,693 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlSoftware and IT services | 1,470.809 arena points 95% confidence interval: ±5.639The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,496.316 arena pointsHigher measured value 95% confidence interval: ±6.759The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_software_and_it_servicesTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 20,180 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 10,881 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlSoftware and IT services | 1,473.269 arena points 95% confidence interval: ±5.679The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,496.316 arena pointsHigher measured value 95% confidence interval: ±6.759The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_software_and_it_servicesTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 20,086 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 10,881 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlSpanish | 1,432.449 arena points 95% confidence interval: ±16.767The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,482.536 arena pointsHigher measured value 95% confidence interval: ±21.801The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:spanishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,532 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 806 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlSpanish | 1,432.679 arena points 95% confidence interval: ±17.246The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,482.536 arena pointsHigher measured value 95% confidence interval: ±21.801The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:spanishTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,427 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 806 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlWriting, literature and language | 1,418.104 arena points 95% confidence interval: ±6.732The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,456.431 arena pointsHigher measured value 95% confidence interval: ±8.076The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_writing_and_literature_and_languageTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 11,766 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,806 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlWriting, literature and language | 1,421.414 arena points 95% confidence interval: ±6.736The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,456.431 arena pointsHigher measured value 95% confidence interval: ±8.076The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_writing_and_literature_and_languageTest setup not documented as identicalNo direct winnerDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control GLM-5.2: Snapshot: glm-5.2-max, Reasoning: max, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 11,864 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,806 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
How to read this comparison
Winning one benchmark is not an overall verdict
Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.
Prices use official API rates per 1M tokens. Web subscriptions and cloud platform surcharges can differ.
Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.
More matchups
Related LLM comparisons
Compare DeepSeek-V4-Flash and GLM-5.2 with other leading models using the same data and benchmark logic.
View the complete LLM comparison