Head-to-head comparison
DeepSeek-V4-Pro vs. Mistral Large 3
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
58
shared result series
1
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-Pro | Mistral Large 3 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Released | Apr 24, 2026 | Dec 2, 2025 |
| Availability | Preview | Active |
| Model type | Open Weights | Open Weights |
| Parameters | 1.6T, 49B active | 675B, 41B active |
| Architecture | Mixture of Experts | Mixture of Experts |
| Context window | 1,000,000 tokens | 256,000 tokens |
| Knowledge cutoff | Not published | Not published |
| Technical sources | Model, Context | Model |
| API pricing per 1M tokens | ||
| API input | $0.43 | $0.5 |
| API output | $0.87 | $1.5 |
| Cache read | $0. | Not listed |
| 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-ProMistral Large 3
API inputUSD per 1M tokens, base tier
DeepSeek-V4-Pro$0.435Lower price
Mistral Large 3$0.5
API outputUSD per 1M tokens, base tier
DeepSeek-V4-Pro$0.87Lower price
Mistral Large 3$1.5
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.
58 shared result series
DeepSeek-V4-ProMistral Large 3
Arena Text, Style ControlOverall. Higher is better. No documented setup difference
DeepSeek-V4-Pro1,458.103 arena pointsWinner
Mistral Large 31,414.798 arena points
Arena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
DeepSeek-V4-Pro1,455.61 arena pointsHigher measured value
Mistral Large 31,414.798 arena points
Arena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference
DeepSeek-V4-Pro1,460.638 arena pointsWinner
Mistral Large 31,412.96 arena points
Arena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
DeepSeek-V4-Pro1,447.754 arena pointsHigher measured value
Mistral Large 31,412.96 arena points
Arena Text, Style ControlChinese. Higher is better. No documented setup difference
DeepSeek-V4-Pro1,494.914 arena pointsWinner
Mistral Large 31,429.195 arena points
Arena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
DeepSeek-V4-Pro1,500.632 arena pointsHigher measured value
Mistral Large 31,429.195 arena points
Arena Text, Style ControlCoding. Higher is better. No documented setup difference
DeepSeek-V4-Pro1,502.053 arena pointsWinner
Mistral Large 31,468.172 arena points
Arena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
DeepSeek-V4-Pro1,488.583 arena pointsHigher measured value
Mistral Large 31,468.172 arena points
Arena Text, Style ControlCreative writing. Higher is better. No documented setup difference
DeepSeek-V4-Pro1,445.32 arena pointsWinner
Mistral Large 31,374.812 arena points
Arena Text, Style ControlCreative writing. Higher is better. Test setup not documented as identical
DeepSeek-V4-Pro1,440.915 arena pointsHigher measured value
Mistral Large 31,374.812 arena points
Arena Text, Style ControlEnglish. Higher is better. No documented setup difference
DeepSeek-V4-Pro1,467.841 arena pointsWinner
Mistral Large 31,428.092 arena points
Arena Text, Style ControlEnglish. Higher is better. Test setup not documented as identical
DeepSeek-V4-Pro1,466.432 arena pointsHigher measured value
Mistral Large 31,428.092 arena points
| Benchmark and task | DeepSeek-V4-Pro | Mistral Large 3 | Comparability | Source |
|---|---|---|---|---|
| Arena Text, Style ControlOverall | 1,458.103 arena pointsWinner 95% confidence interval: ±4.022The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,414.798 arena points 95% confidence interval: ±3.173The 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:overallNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 54,288 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 59,196 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlOverall | 1,455.61 arena pointsHigher measured value 95% confidence interval: ±4.089The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,414.798 arena points 95% confidence interval: ±3.173The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 51,670 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 59,196 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlBusiness, management and finance | 1,460.638 arena pointsWinner 95% confidence interval: ±6.951The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,412.96 arena points 95% confidence interval: ±6.188The 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_operationsNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 10,715 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 11,241 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlBusiness, management and finance | 1,447.754 arena pointsHigher measured value 95% confidence interval: ±7.037The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,412.96 arena points 95% confidence interval: ±6.188The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 10,363 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 11,241 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlChinese | 1,494.914 arena pointsWinner 95% confidence interval: ±12.109The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,429.195 arena points 95% confidence interval: ±11.167The 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:chineseNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,881 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,176 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlChinese | 1,500.632 arena pointsHigher measured value 95% confidence interval: ±12.361The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,429.195 arena points 95% confidence interval: ±11.167The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,780 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,176 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCoding | 1,502.053 arena pointsWinner 95% confidence interval: ±6.098The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,468.172 arena points 95% confidence interval: ±5.487The 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:codingNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 16,219 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 14,576 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCoding | 1,488.583 arena pointsHigher measured value 95% confidence interval: ±6.254The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,468.172 arena points 95% confidence interval: ±5.487The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 15,137 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 14,576 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCreative writing | 1,445.32 arena pointsWinner 95% confidence interval: ±7.549The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,374.812 arena points 95% confidence interval: ±6.696The 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_writingNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 8,993 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 9,516 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCreative writing | 1,440.915 arena pointsHigher measured value 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. | 1,374.812 arena points 95% confidence interval: ±6.696The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 8,630 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 9,516 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEnglish | 1,467.841 arena pointsWinner 95% confidence interval: ±5.232The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,428.092 arena points 95% confidence interval: ±4.322The 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:englishNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 23,938 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 27,057 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEnglish | 1,466.432 arena pointsHigher measured value 95% confidence interval: ±5.282The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,428.092 arena points 95% confidence interval: ±4.322The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 22,716 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 27,057 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 | 1,434.546 arena pointsWinner 95% confidence interval: ±6.838The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,374.062 arena points 95% confidence interval: ±6.028The 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_mediaNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 11,864 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 11,988 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 | 1,430.998 arena pointsHigher measured value 95% confidence interval: ±6.917The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,374.062 arena points 95% confidence interval: ±6.028The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 11,417 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 11,988 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExcluding ties | 1,461.846 arena pointsWinner 95% confidence interval: ±5.269The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,402.073 arena points 95% confidence interval: ±4.45The 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_tiesNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 41,089 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 42,743 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExcluding ties | 1,457.694 arena pointsHigher measured value 95% confidence interval: ±5.283The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,402.073 arena points 95% confidence interval: ±4.45The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 39,206 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 42,743 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExpert prompts | 1,482.281 arena pointsWinner 95% confidence interval: ±8.872The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,425.617 arena points 95% confidence interval: ±8.821The 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:expertNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 5,438 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,022 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExpert prompts | 1,474.832 arena pointsHigher measured value 95% confidence interval: ±9.032The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,425.617 arena points 95% confidence interval: ±8.821The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 5,066 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,022 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlFrench | 1,483.706 arena pointsWinner 95% confidence interval: ±15.355The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,436.959 arena points 95% confidence interval: ±16.748The 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:frenchNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,116 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,573 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlFrench | 1,470.225 arena pointsHigher measured value 95% confidence interval: ±15.468The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,436.959 arena points 95% confidence interval: ±16.748The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 1,986 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,573 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlGerman | 1,465.944 arena pointsWinner 95% confidence interval: ±20.28The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,404.865 arena points 95% confidence interval: ±20.292The 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:germanNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 950 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 938 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlGerman | 1,458.46 arena pointsHigher measured value 95% confidence interval: ±20.895The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,404.865 arena points 95% confidence interval: ±20.292The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 877 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 938 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts | 1,480.536 arena pointsWinner 95% confidence interval: ±4.713The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,431.831 arena points 95% confidence interval: ±3.992The 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_promptsNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 36,125 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 35,076 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts | 1,474.247 arena pointsHigher measured value 95% confidence interval: ±4.773The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,431.831 arena points 95% confidence interval: ±3.992The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 34,588 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 35,076 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts, English | 1,484.514 arena pointsWinner 95% confidence interval: ±6.003The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,439.235 arena points 95% confidence interval: ±5.258The 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_englishNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 16,817 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,489 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts, English | 1,482.312 arena pointsHigher measured value 95% confidence interval: ±6.088The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,439.235 arena points 95% confidence interval: ±5.258The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 15,915 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,489 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlInstruction following | 1,453.655 arena pointsWinner 95% confidence interval: ±5.745The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,401.455 arena points 95% confidence interval: ±5.054The 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_followingNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 18,719 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 17,943 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlInstruction following | 1,449.35 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. | 1,401.455 arena points 95% confidence interval: ±5.054The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 17,752 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 17,943 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlJapanese | 1,461.924 arena pointsWinner 95% confidence interval: ±25.076The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,372.852 arena points 95% confidence interval: ±27.094The 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:japaneseNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 677 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 532 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlJapanese | 1,429.848 arena pointsHigher measured value 95% confidence interval: ±25.425The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,372.852 arena points 95% confidence interval: ±27.094The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 629 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 532 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlKorean | 1,418.422 arena pointsWinner 95% confidence interval: ±19.586The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,347.595 arena points 95% confidence interval: ±20.301The 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:koreanNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 1,070 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 983 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlKorean | 1,431.798 arena pointsHigher measured value 95% confidence interval: ±20.36The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,347.595 arena points 95% confidence interval: ±20.301The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 958 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 983 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLegal and government | 1,473.155 arena pointsWinner 95% confidence interval: ±9.905The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,422.186 arena points 95% confidence interval: ±9.342The 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_governmentNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 4,245 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,397 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLegal and government | 1,472.404 arena pointsHigher measured value 95% confidence interval: ±10.073The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,422.186 arena points 95% confidence interval: ±9.342The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 4,056 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,397 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 | 1,481.533 arena pointsWinner 95% confidence interval: ±7.371The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,427.837 arena points 95% confidence interval: ±6.466The 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_scienceNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 8,617 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 9,572 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 | 1,478.57 arena pointsHigher measured value 95% confidence interval: ±7.454The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,427.837 arena points 95% confidence interval: ±6.466The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 8,168 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 9,572 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLonger queries | 1,472.734 arena pointsWinner 95% confidence interval: ±5.523The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,418.594 arena points 95% confidence interval: ±4.972The 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_queryNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 24,005 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 20,121 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLonger queries | 1,466.572 arena pointsHigher measured value 95% confidence interval: ±5.598The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,418.594 arena points 95% confidence interval: ±4.972The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 22,884 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 20,121 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMath | 1,444.797 arena pointsWinner 95% confidence interval: ±11.56The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,404.068 arena points 95% confidence interval: ±10.174The 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:mathNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,862 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,533 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMath | 1,468.86 arena pointsHigher measured value 95% confidence interval: ±12.286The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,404.068 arena points 95% confidence interval: ±10.174The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,503 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,533 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMathematical professions | 1,460.06 arena pointsWinner 95% confidence interval: ±11.553The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,418.682 arena points 95% confidence interval: ±11.451The 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_mathematicalNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 3,005 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 2,868 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMathematical professions | 1,468.576 arena pointsHigher measured value 95% confidence interval: ±12.161The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,418.682 arena points 95% confidence interval: ±11.451The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,683 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 2,868 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMedicine and healthcare | 1,477.305 arena pointsWinner 95% confidence interval: ±10.595The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,432.596 arena points 95% confidence interval: ±9.78The 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_healthcareNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 3,764 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,088 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMedicine and healthcare | 1,485.153 arena pointsHigher measured value 95% confidence interval: ±10.758The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,432.596 arena points 95% confidence interval: ±9.78The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 3,585 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,088 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMulti-turn | 1,477.081 arena pointsWinner 95% confidence interval: ±7.236The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,421.924 arena points 95% confidence interval: ±6.397The 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:multi_turnNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 9,808 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,237 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMulti-turn | 1,455.791 arena pointsHigher measured value 95% confidence interval: ±7.356The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,421.924 arena points 95% confidence interval: ±6.397The 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:multi_turnTest setup not documented as identicalNo direct winnerDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 9,151 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,237 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlNon-English | 1,445.283 arena pointsWinner 95% confidence interval: ±4.853The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,398.241 arena points 95% confidence interval: ±4.043The 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_englishNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 30,350 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 32,134 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlNon-English | 1,441.433 arena pointsHigher measured value 95% confidence interval: ±4.93The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,398.241 arena points 95% confidence interval: ±4.043The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 28,950 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 32,134 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlPolish | 1,462.982 arena pointsWinner 95% confidence interval: ±18.614The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,419.007 arena points 95% confidence interval: ±15.852The 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:polishNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 1,067 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,417 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlPolish | 1,462.154 arena pointsHigher measured value 95% confidence interval: ±18.622The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,419.007 arena points 95% confidence interval: ±15.852The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 1,049 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,417 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlRussian | 1,458.488 arena pointsWinner 95% confidence interval: ±8.692The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,409.573 arena points 95% confidence interval: ±7.885The 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:russianNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 5,725 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,987 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlRussian | 1,459.053 arena pointsHigher measured value 95% confidence interval: ±8.778The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,409.573 arena points 95% confidence interval: ±7.885The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 5,573 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,987 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 | 1,492.65 arena pointsWinner 95% confidence interval: ±5.414The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,456.428 arena points 95% confidence interval: ±4.685The 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_servicesNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 22,338 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 22,035 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 | 1,483.295 arena pointsHigher measured value 95% confidence interval: ±5.497The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,456.428 arena points 95% confidence interval: ±4.685The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 21,186 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 22,035 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlSpanish | 1,455.955 arena pointsWinner 95% confidence interval: ±16.149The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,411.23 arena points 95% confidence interval: ±16.163The 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:spanishNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 1,656 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,603 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlSpanish | 1,450.859 arena pointsHigher measured value 95% confidence interval: ±16.308The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,411.23 arena points 95% confidence interval: ±16.163The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 1,615 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,603 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 | 1,451.594 arena pointsWinner 95% confidence interval: ±6.517The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,389.648 arena points 95% confidence interval: ±5.636The 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_languageNo documented setup differenceWinner: DeepSeek-V4-ProDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 13,160 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,904 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 | 1,443.409 arena pointsHigher measured value 95% confidence interval: ±6.601The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,389.648 arena points 95% confidence interval: ±5.636The 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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 12,742 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,904 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-Pro and Mistral Large 3 with other leading models using the same data and benchmark logic.
View the complete LLM comparison