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.
- shared result series
- 61
- distinct benchmarks
- 2
- latest retrieval
- 2026-09-04
Change model selection
Specifications
General specifications
Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.
| 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 |
Pricing
API pricing compared
The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
| Price type | DeepSeek-V4-Flash | GLM-5.2 |
|---|---|---|
| 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 | 07/30/2026 Source | 07/30/2026 Source |
DeepSeek-V4-FlashGLM-5.2
API inputUSD per 1M tokens, base tier
DeepSeek-V4-FlashLower price$0.14
GLM-5.2$1.4
API outputUSD per 1M tokens, base tier
DeepSeek-V4-FlashLower price$0.28
GLM-5.2$4.4
Cache readUSD per 1M tokens, base tier
DeepSeek-V4-FlashLower price$0.003
GLM-5.2$0.26
Key to the marks:better valuebetter, but not conclusivetie
Pricing by provider
Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.
| Model | Provider | Purchase route and tariff | Input per 1M tokens | Output per 1M tokens | Source |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash | DeepSeek | Direct from developerStandard API | $0.14 | $0.28 | Source07/30/2026 |
| Alibaba | Via OpenRouteralibaba | $0.352 | $1.056 | Source09/07/2026 | |
| AtlasCloud | Via OpenRouteratlas-cloud/fp4 | $0.44 | $1.32 | Source09/07/2026 | |
| Baidu | Via OpenRouterbaidu/fp8 | $0.14 | $0.28 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp8#1 | $0.13 | $0.26 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp8#2 | $0.13 | $0.26 | Source09/07/2026 | |
| Cloudflare | Via OpenRoutercloudflare | $0.44 | $1.32 | Source09/07/2026 | |
| CoreWeave | Via OpenRoutercoreweave/fp8 | $0.13 | $0.28 | Source09/07/2026 | |
| DeepInfra | Via OpenRouterdeepinfra/fp8 | $0.06 | $0.18 | Source09/07/2026 | |
| DeepSeek | Via OpenRouterdeepseek | $0.22 | $0.66 | Source09/07/2026 | |
| DigitalOcean | Via OpenRouterdigitalocean | $0.08 | $0.252 | Source09/07/2026 | |
| Fireworks | Via OpenRouterfireworks | $0.22 | $0.66 | Source09/07/2026 | |
| GMICloud | Via OpenRoutergmicloud/fp8 | $0.352 | $1.056 | Source09/07/2026 | |
| Inceptron | Via OpenRouterinceptron/fp4 | $0.13 | $0.28 | Source09/07/2026 | |
| Makora | Via OpenRoutermakora | $0.09 | $0.195 | Source09/07/2026 | |
| Mancer 2 | Via OpenRoutermancer/fp8 | $0.15 | $0.5 | Source09/07/2026 | |
| Morph | Via OpenRoutermorph/bf16 | $0.1234 | $0.3475 | Source09/07/2026 | |
| NextBit | Via OpenRouternextbit/fp8 | $0.4 | $1.2 | Source09/07/2026 | |
| Novita | Via OpenRouternovita/fp8 | $0.4092 | $1.2276 | Source09/07/2026 | |
| OpenInference | Via OpenRouteropen-inference/fp8 | $0.05 | $0.16 | Source09/07/2026 | |
| Parasail | Via OpenRouterparasail/fp8 | $0.14 | $0.28 | Source09/07/2026 | |
| Phala | Via OpenRouterphala | $0.44 | $1.32 | Source09/07/2026 | |
| Reka | Via OpenRouterreka/fp4 | $0.11 | $0.66 | Source09/07/2026 | |
| Relace | Via OpenRouterrelace/fp4 | Lowest listed price: $0.045 | Lowest listed price: $0.09 | Source09/07/2026 | |
| Sail Research | Via OpenRoutersail-research/fp4 | $0.065 | $0.18 | Source09/07/2026 | |
| SiliconFlow | Via OpenRoutersiliconflow/fp8 | $0.22 | $0.66 | Source09/07/2026 | |
| StreamLake | Via OpenRouterstreamlake/fp8 | $0.088 | $0.264 | Source09/07/2026 | |
| Together | Via OpenRoutertogether | $0.14 | $0.28 | Source09/07/2026 | |
| Venice | Via OpenRoutervenice | $0.175 | $0.35 | Source09/07/2026 | |
| Wafer | Via OpenRouterwafer/fast | $0.1 | $0.25 | Source09/07/2026 | |
| GLM-5.2 | Z.ai | Direct from developerStandard API | $1.4 | $4.4 | Source07/30/2026 |
| Alibaba | Via OpenRouteralibaba/fast | $2.31 | $7.26 | Source09/07/2026 | |
| Alibaba | Via OpenRouteralibaba/fp8 | $0.966 | $3.036 | Source09/07/2026 | |
| Ambient | Via OpenRouterambient/fp8 | $0.6 | $2 | Source09/07/2026 | |
| AtlasCloud | Via OpenRouteratlas-cloud/fp8 | $0.938 | $2.948 | Source09/07/2026 | |
| Baidu | Via OpenRouterbaidu/fp8 | $1.4 | $4.4 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fast#1 | $2.1 | $6.6 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fast#2 | $2.1 | $6.6 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp8#1 | $1.4 | $4.4 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp8#2 | $1.4 | $4.4 | Source09/07/2026 | |
| Cloudflare | Via OpenRoutercloudflare | $1.4 | $4.4 | Source09/07/2026 | |
| CoreWeave | Via OpenRoutercoreweave/fp4 | $0.76 | $2.42 | Source09/07/2026 | |
| Crusoe | Via OpenRoutercrusoe/fp8 | $1.4 | $4.4 | Source09/07/2026 | |
| Decart | Via OpenRouterdecart/fast | $1.26 | $3.96 | Source09/07/2026 | |
| Decart | Via OpenRouterdecart/fp4 | $0.684 | $2.28 | Source09/07/2026 | |
| DeepInfra | Via OpenRouterdeepinfra/fp4 | Lowest listed price: $0.4875 | Lowest listed price: $1.56 | Source09/07/2026 | |
| DigitalOcean | Via OpenRouterdigitalocean | $0.7 | $2.2 | Source09/07/2026 | |
| Fireworks | Via OpenRouterfireworks | $1.4 | $4.4 | Source09/07/2026 | |
| Fireworks | Via OpenRouterfireworks/fast | $2.1 | $6.6 | Source09/07/2026 | |
| Fireworks | Via OpenRouterfireworks/fast-us | $2.1 | $6.6 | Source09/07/2026 | |
| Friendli | Via OpenRouterfriendli | $1.4 | $4.4 | Source09/07/2026 | |
| GMICloud | Via OpenRoutergmicloud/fp8 | $1.05 | $3.3 | Source09/07/2026 | |
| Inceptron | Via OpenRouterinceptron/fp4 | $1.25 | $2.99 | Source09/07/2026 | |
| Mistral | Via OpenRoutermistral | $1.4 | $4.4 | Source09/07/2026 | |
| Mistral | Via OpenRoutermistral/eu | $1.54 | $4.84 | Source09/07/2026 | |
| Mistral | Via OpenRoutermistral/zdr | $1.4 | $4.4 | Source09/07/2026 | |
| Novita | Via OpenRouternovita/fp8 | $0.5586 | $1.7556 | Source09/07/2026 | |
| Parasail | Via OpenRouterparasail/fp4 | $1.4 | $4.4 | Source09/07/2026 | |
| Phala | Via OpenRouterphala/fp8 | $1.26 | $3 | Source09/07/2026 | |
| SiliconFlow | Via OpenRoutersiliconflow/fp8 | $1.19 | $3.74 | Source09/07/2026 | |
| StreamLake | Via OpenRouterstreamlake/fp8 | $0.5446 | $1.7116 | Source09/07/2026 | |
| Together | Via OpenRoutertogether | $1.4 | $4.4 | Source09/07/2026 | |
| Venice | Via OpenRoutervenice/fp8 | $1.4 | $4.4 | Source09/07/2026 | |
| Z.AI | Via OpenRouterz-ai/fp8 | $1.4 | $4.4 | Source09/07/2026 |
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.
Capability profile from matched benchmarks
Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.
Not enough directly matched categories for a reliable radar
Only 1 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.
DeepSeek-V4-FlashGLM-5.2
CyberBenchOverall. Higher is better. No documented setup difference
DeepSeek-V4-Flash66.716 %
GLM-5.2Winner77.359 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,435.816
GLM-5.2Higher measured value1,471.886
CyberBenchPatch. Higher is better. No documented setup difference
DeepSeek-V4-Flash72.414 %
GLM-5.2Winner81.034 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,438.462
GLM-5.2Higher measured value1,471.886
CyberBenchPoC. Higher is better. No documented setup difference
DeepSeek-V4-Flash61.017 %
GLM-5.2Winner73.684 %
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,437.854
GLM-5.2Higher measured value1,460.145
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,434.968
GLM-5.2Higher measured value1,460.145
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,472.677
GLM-5.2Higher measured value1,516.828
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,479.62
GLM-5.2Higher measured value1,516.828
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,483.101
GLM-5.2Higher measured value1,509.051
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,479.449
GLM-5.2Higher measured value1,509.051
LMArena Text, Style ControlCreative writing. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,408.18
GLM-5.2Higher measured value1,452.152
Key to the marks:better valuebetter, but not conclusivetie
| Benchmark and task | DeepSeek-V4-Flash | GLM-5.2 | Source |
|---|---|---|---|
CyberBenchOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 66.716 % | Winner77.359 % | Vals AISource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlOverallTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 48,963 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 33,758 anonymous pairwise votes. | 1,435.816 95% confidence interval: ±4.15The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,471.886 95% confidence interval: ±4.729The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
CyberBenchPatchTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 72.414 % | Winner81.034 % | Vals AISource detailsData as of: 08/03/2026 |
LMArena Text, Style ControlOverallTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 48,705 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 33,758 anonymous pairwise votes. | 1,438.462 95% confidence interval: ±4.21The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,471.886 95% confidence interval: ±4.729The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
CyberBenchPoCTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 61.017 % | Winner73.684 % | Vals AISource detailsData as of: 08/03/2026 |
LMArena Text, Style ControlBusiness, management and financeTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 9,911 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,609 anonymous pairwise votes. | 1,437.854 95% confidence interval: ±7.128The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,460.145 95% confidence interval: ±8.046The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlBusiness, management and financeTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 10,060 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,609 anonymous pairwise votes. | 1,434.968 95% confidence interval: ±7.142The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,460.145 95% confidence interval: ±8.046The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlChineseTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 2,530 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,084 anonymous pairwise votes. | 1,472.677 95% confidence interval: ±12.483The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,516.828 95% confidence interval: ±13.481The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlChineseTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 2,509 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,084 anonymous pairwise votes. | 1,479.62 95% confidence interval: ±12.459The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,516.828 95% confidence interval: ±13.481The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCodingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 14,346 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 9,517 anonymous pairwise votes. | 1,483.101 95% confidence interval: ±6.376The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,509.051 95% confidence interval: ±7.106The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCodingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 14,310 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 9,517 anonymous pairwise votes. | 1,479.449 95% confidence interval: ±6.409The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,509.051 95% confidence interval: ±7.106The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCreative writingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 7,972 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,464 anonymous pairwise votes. | 1,408.18 95% confidence interval: ±7.747The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,452.152 95% confidence interval: ±8.384The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCreative writingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 8,029 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 6,464 anonymous pairwise votes. | 1,408.903 95% confidence interval: ±7.781The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,452.152 95% confidence interval: ±8.384The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 21,931 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 14,493 anonymous pairwise votes. | 1,445.287 95% confidence interval: ±5.383The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,479.42 95% confidence interval: ±6.007The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 21,747 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 14,493 anonymous pairwise votes. | 1,449.894 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. | Higher measured value1,479.42 95% confidence interval: ±6.007The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEntertainment, sports and mediaTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 10,423 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 8,237 anonymous pairwise votes. | 1,405.349 95% confidence interval: ±7.122The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,441.6 95% confidence interval: ±7.595The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEntertainment, sports and mediaTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 10,655 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 8,237 anonymous pairwise votes. | 1,406.152 95% confidence interval: ±7.06The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,441.6 95% confidence interval: ±7.595The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExcluding tiesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 36,983 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 25,084 anonymous pairwise votes. | 1,431.271 95% confidence interval: ±5.416The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,480.216 95% confidence interval: ±6.156The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExcluding tiesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 37,039 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 25,084 anonymous pairwise votes. | 1,435.7 95% confidence interval: ±5.462The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,480.216 95% confidence interval: ±6.156The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExpert promptsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 4,904 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 3,611 anonymous pairwise votes. | 1,458.425 95% confidence interval: ±9.147The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,490.497 95% confidence interval: ±10.359The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExpert promptsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 4,907 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 3,611 anonymous pairwise votes. | 1,467.744 95% confidence interval: ±9.211The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,490.497 95% confidence interval: ±10.359The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlFrenchTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 1,909 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,218 anonymous pairwise votes. | 1,444.246 95% confidence interval: ±15.542The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,489.341 95% confidence interval: ±18.469The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlFrenchTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 1,872 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,218 anonymous pairwise votes. | 1,457.512 95% confidence interval: ±15.76The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,489.341 95% confidence interval: ±18.469The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlGermanTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 834 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 615 anonymous pairwise votes. | 1,423.985 95% confidence interval: ±21.432The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,471.171 95% confidence interval: ±24.381The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlGermanTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 881 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 615 anonymous pairwise votes. | 1,434.001 95% confidence interval: ±20.992The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,471.171 95% confidence interval: ±24.381The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard promptsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 32,576 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 22,303 anonymous pairwise votes. | 1,459.19 95% confidence interval: ±4.879The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,492.244 95% confidence interval: ±5.461The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard promptsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 32,479 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 22,303 anonymous pairwise votes. | 1,458.492 95% confidence interval: ±4.934The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,492.244 95% confidence interval: ±5.461The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard prompts, EnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 15,327 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 9,760 anonymous pairwise votes. | 1,464.306 95% confidence interval: ±6.191The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,493.409 95% confidence interval: ±6.978The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard prompts, EnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 15,135 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 9,760 anonymous pairwise votes. | 1,465.194 95% confidence interval: ±6.261The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,493.409 95% confidence interval: ±6.978The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlInstruction followingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 16,772 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 11,818 anonymous pairwise votes. | 1,428.139 95% confidence interval: ±5.955The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,465.971 95% confidence interval: ±6.527The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlInstruction followingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 16,813 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 11,818 anonymous pairwise votes. | 1,433.908 95% confidence interval: ±6.024The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,465.971 95% confidence interval: ±6.527The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlJapaneseTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 633 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 500 anonymous pairwise votes. | 1,397.389 95% confidence interval: ±25.351The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,452.789 95% confidence interval: ±28.439The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlJapaneseTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 600 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 500 anonymous pairwise votes. | 1,422.217 95% confidence interval: ±25.99The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,452.789 95% confidence interval: ±28.439The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlKoreanTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 867 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 679 anonymous pairwise votes. | 1,394.225 95% confidence interval: ±21.434The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,437.093 95% confidence interval: ±23.495The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlKoreanTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 909 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 679 anonymous pairwise votes. | 1,374.943 95% confidence interval: ±21.551The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,437.093 95% confidence interval: ±23.495The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLegal and governmentTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 3,892 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,729 anonymous pairwise votes. | 1,449.174 95% confidence interval: ±10.185The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,480.415 95% confidence interval: ±11.911The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLegal and governmentTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 3,872 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,729 anonymous pairwise votes. | 1,459.091 95% confidence interval: ±10.242The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,480.415 95% confidence interval: ±11.911The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLife, physical and social scienceTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 7,776 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 5,513 anonymous pairwise votes. | 1,458.608 95% confidence interval: ±7.61The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,490.799 95% confidence interval: ±8.502The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLife, physical and social scienceTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 7,968 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 5,513 anonymous pairwise votes. | 1,460.882 95% confidence interval: ±7.588The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,490.799 95% confidence interval: ±8.502The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLonger queriesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 21,561 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 15,559 anonymous pairwise votes. | 1,448.456 95% confidence interval: ±5.733The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,482.088 95% confidence interval: ±6.173The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLonger queriesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 21,664 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 15,559 anonymous pairwise votes. | 1,449.036 95% confidence interval: ±5.731The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,482.088 95% confidence interval: ±6.173The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 1,562 anonymous pairwise votes. | 1,425.091 95% confidence interval: ±12.209The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,475.761 95% confidence interval: ±14.884The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 2,459 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,562 anonymous pairwise votes. | 1,441.301 95% confidence interval: ±12.311The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,475.761 95% confidence interval: ±14.884The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathematical professionsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 2,746 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,839 anonymous pairwise votes. | 1,431.608 95% confidence interval: ±11.935The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,485.86 95% confidence interval: ±14.134The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathematical professionsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 2,607 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,839 anonymous pairwise votes. | 1,443.348 95% confidence interval: ±12.313The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,485.86 95% confidence interval: ±14.134The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMedicine and healthcareTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 3,429 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,448 anonymous pairwise votes. | 1,459.604 95% confidence interval: ±10.945The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,485.043 95% confidence interval: ±12.667The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMedicine and healthcareTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 3,495 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 2,448 anonymous pairwise votes. | 1,462.945 95% confidence interval: ±10.866The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,485.043 95% confidence interval: ±12.667The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMulti-turnTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 8,820 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 5,576 anonymous pairwise votes. | 1,452.356 95% confidence interval: ±7.462The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,468.85 95% confidence interval: ±8.633The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMulti-turnTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 8,674 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 5,576 anonymous pairwise votes. | 1,445.683 95% confidence interval: ±7.508The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,468.85 95% confidence interval: ±8.633The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlNon-EnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 27,030 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 19,262 anonymous pairwise votes. | 1,423.067 95% confidence interval: ±5.056The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,457.477 95% confidence interval: ±5.556The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlNon-EnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 26,956 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 19,262 anonymous pairwise votes. | 1,422.651 95% confidence interval: ±5.123The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,457.477 95% confidence interval: ±5.556The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlPolishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 1,005 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 578 anonymous pairwise votes. | 1,439.462 95% confidence interval: ±18.965The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,454.033 95% confidence interval: ±24.65The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlPolishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 1,014 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 578 anonymous pairwise votes. | 1,430.358 95% confidence interval: ±18.866The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,454.033 95% confidence interval: ±24.65The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlRussianTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 5,250 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 3,522 anonymous pairwise votes. | 1,433.186 95% confidence interval: ±8.845The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,466.024 95% confidence interval: ±10.342The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlRussianTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 5,207 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 3,522 anonymous pairwise votes. | 1,437.38 95% confidence interval: ±8.983The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,466.024 95% confidence interval: ±10.342The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSoftware and IT servicesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 20,105 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 13,508 anonymous pairwise votes. | 1,471.075 95% confidence interval: ±5.634The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,500.839 95% confidence interval: ±6.248The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSoftware and IT servicesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 20,031 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 13,508 anonymous pairwise votes. | 1,473.269 95% confidence interval: ±5.664The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,500.839 95% confidence interval: ±6.248The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSpanishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 1,548 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,000 anonymous pairwise votes. | 1,433.026 95% confidence interval: ±16.368The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,479.664 95% confidence interval: ±19.627The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSpanishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 1,443 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 1,000 anonymous pairwise votes. | 1,431.772 95% confidence interval: ±16.888The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,479.664 95% confidence interval: ±19.627The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlWriting, literature and languageTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 11,742 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 8,835 anonymous pairwise votes. | 1,417.982 95% confidence interval: ±6.712The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,456.422 95% confidence interval: ±7.279The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlWriting, literature and languageTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-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 11,861 anonymous pairwise votes.GLM-5.2: Style-controlled Arena rating from 8,835 anonymous pairwise votes. | 1,421.395 95% confidence interval: ±6.717The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,456.422 95% confidence interval: ±7.279The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
Key to the marks:better valuebetter, but not conclusivetie | |||
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.
The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.
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.