Head-to-head comparison
GPT-5.4 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 | GPT-5.4 | Mistral Large 3 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Released | Mar 2026 | Dec 2, 2025 |
| Availability | Active | Active |
| Model type | Proprietary | Open Weights |
| Parameters | Not published | 675B, 41B active |
| Architecture | Not published | Mixture of Experts |
| Context window | 1,050,000 tokens | 256,000 tokens |
| Knowledge cutoff | August 31, 2025 | Not published |
| Technical sources | Model | Model |
| API pricing per 1M tokens | ||
| API input | $2.5 ≤272K / $5 >272K | $0.5 |
| API output | $15 ≤272K / $22.5 >272K | $1.5 |
| Cache read | $0.25 ≤272K / $0.5 >272K | 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 |
GPT-5.4Mistral Large 3
API inputUSD per 1M tokens, base tier
GPT-5.4$2.5
Mistral Large 3$0.5Lower price
API outputUSD per 1M tokens, base tier
GPT-5.4$15
Mistral Large 3$1.5Lower price
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
GPT-5.4Mistral Large 3
Arena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.41,465.439 arena pointsWinner
Mistral Large 31,414.798 arena points
Arena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.41,476.571 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
GPT-5.41,474.218 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
GPT-5.41,483.617 arena pointsHigher measured value
Mistral Large 31,412.96 arena points
Arena Text, Style ControlChinese. Higher is better. No documented setup difference
GPT-5.41,496.688 arena pointsWinner
Mistral Large 31,429.195 arena points
Arena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
GPT-5.41,506.007 arena pointsHigher measured value
Mistral Large 31,429.195 arena points
Arena Text, Style ControlCoding. Higher is better. No documented setup difference
GPT-5.41,513.75 arena pointsWinner
Mistral Large 31,468.172 arena points
Arena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
GPT-5.41,520.704 arena pointsHigher measured value
Mistral Large 31,468.172 arena points
Arena Text, Style ControlCreative writing. Higher is better. No documented setup difference
GPT-5.41,436.291 arena pointsWinner
Mistral Large 31,374.812 arena points
Arena Text, Style ControlCreative writing. Higher is better. Test setup not documented as identical
GPT-5.41,444.387 arena pointsHigher measured value
Mistral Large 31,374.812 arena points
Arena Text, Style ControlEnglish. Higher is better. No documented setup difference
GPT-5.41,468.758 arena pointsWinner
Mistral Large 31,428.092 arena points
Arena Text, Style ControlEnglish. Higher is better. Test setup not documented as identical
GPT-5.41,478.413 arena pointsHigher measured value
Mistral Large 31,428.092 arena points
| Benchmark and task | GPT-5.4 | Mistral Large 3 | Comparability | Source |
|---|---|---|---|---|
| Arena Text, Style ControlOverall | 1,465.439 arena pointsWinner 95% confidence interval: ±3.814The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 63,759 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 | 1,476.571 arena pointsHigher measured value 95% confidence interval: ±3.887The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 60,819 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 | 1,474.218 arena pointsWinner 95% confidence interval: ±6.56The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,072 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 | 1,483.617 arena pointsHigher measured value 95% confidence interval: ±6.683The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,373 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 | 1,496.688 arena pointsWinner 95% confidence interval: ±11.202The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,574 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 | 1,506.007 arena pointsHigher measured value 95% confidence interval: ±11.398The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,369 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 | 1,513.75 arena pointsWinner 95% confidence interval: ±5.977The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 17,752 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 | 1,520.704 arena pointsHigher measured value 95% confidence interval: ±6.02The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 16,515 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 | 1,436.291 arena pointsWinner 95% confidence interval: ±7.077The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,314 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 | 1,444.387 arena pointsHigher measured value 95% confidence interval: ±7.221The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,119 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 | 1,468.758 arena pointsWinner 95% confidence interval: ±4.955The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 29,658 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 | 1,478.413 arena pointsHigher measured value 95% confidence interval: ±5.006The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 28,120 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 | 1,433.639 arena pointsWinner 95% confidence interval: ±6.465The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,629 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 | 1,443.099 arena pointsHigher measured value 95% confidence interval: ±6.632The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,966 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 | 1,471.723 arena pointsWinner 95% confidence interval: ±4.974The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 48,930 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 | 1,486.146 arena pointsHigher measured value 95% confidence interval: ±5.068The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 46,537 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 | 1,490.915 arena pointsWinner 95% confidence interval: ±8.635The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 6,142 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 | 1,516.663 arena pointsHigher measured value 95% confidence interval: ±8.789The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 5,794 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 | 1,484.736 arena pointsWinner 95% confidence interval: ±14.945The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 2,316 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 | 1,501.631 arena pointsHigher measured value 95% confidence interval: ±15.039The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 2,293 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 | 1,448.583 arena pointsWinner 95% confidence interval: ±20.526The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 956 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 | 1,466.734 arena pointsHigher measured value 95% confidence interval: ±19.582The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,054 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 | 1,487.682 arena pointsWinner 95% confidence interval: ±4.603The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 41,916 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 | 1,498.61 arena pointsHigher measured value 95% confidence interval: ±4.64The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 39,412 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 | 1,486.794 arena pointsWinner 95% confidence interval: ±5.668The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 20,340 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 | 1,495.669 arena pointsHigher measured value 95% confidence interval: ±5.735The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 18,992 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 | 1,461.6 arena pointsWinner 95% confidence interval: ±5.543The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 21,791 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 | 1,473.561 arena pointsHigher measured value 95% confidence interval: ±5.61The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 20,349 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 | 1,449.226 arena pointsWinner 95% confidence interval: ±25.524The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 639 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 | 1,479.952 arena pointsHigher measured value 95% confidence interval: ±26.264The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 634 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 | 1,424.77 arena pointsWinner 95% confidence interval: ±19.666The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,139 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 | 1,434.311 arena pointsHigher measured value 95% confidence interval: ±20.242The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,079 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 | 1,475.533 arena pointsWinner 95% confidence interval: ±9.326The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 5,076 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 | 1,491.12 arena pointsHigher measured value 95% confidence interval: ±9.472The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 4,913 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 | 1,478.92 arena pointsWinner 95% confidence interval: ±6.927The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,340 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 | 1,488.258 arena pointsHigher measured value 95% confidence interval: ±7.051The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 9,911 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 | 1,478.227 arena pointsWinner 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. | 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 27,468 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 | 1,483.605 arena pointsHigher measured value 95% confidence interval: ±5.458The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 26,121 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 | 1,460.364 arena pointsWinner 95% confidence interval: ±10.712The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,344 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 | 1,494.026 arena pointsHigher measured value 95% confidence interval: ±10.982The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,186 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 | 1,471.203 arena pointsWinner 95% confidence interval: ±11.023The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,417 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 | 1,499.572 arena pointsHigher measured value 95% confidence interval: ±11.221The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,238 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 | 1,467.799 arena pointsWinner 95% confidence interval: ±9.744The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 4,695 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 | 1,476.198 arena pointsHigher measured value 95% confidence interval: ±9.964The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 4,483 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 | 1,481.026 arena pointsWinner 95% confidence interval: ±6.734The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,008 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 | 1,494.427 arena pointsHigher measured value 95% confidence interval: ±6.811The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 11,302 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 | 1,458.043 arena pointsWinner 95% confidence interval: ±4.754The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 34,099 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 | 1,468.846 arena pointsHigher measured value 95% confidence interval: ±4.8The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 32,699 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 | 1,473.179 arena pointsWinner 95% confidence interval: ±17.291The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,250 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 | 1,482.154 arena pointsHigher measured value 95% confidence interval: ±17.152The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,298 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 | 1,471.407 arena pointsWinner 95% confidence interval: ±8.204The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 6,797 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 | 1,490.981 arena pointsHigher measured value 95% confidence interval: ±8.413The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 6,401 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 | 1,498.772 arena pointsWinner 95% confidence interval: ±5.275The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 25,369 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 | 1,506.788 arena pointsHigher measured value 95% confidence interval: ±5.317The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 23,913 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 | 1,461.205 arena pointsWinner 95% confidence interval: ±15.24The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,932 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 | 1,456.765 arena pointsHigher measured value 95% confidence interval: ±15.141The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,975 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 | 1,459.832 arena pointsWinner 95% confidence interval: ±6.107The 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: GPT-5.4GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 15,400 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 | 1,466.108 arena pointsHigher measured value 95% confidence interval: ±6.163The 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 winnerGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 15,044 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 GPT-5.4 and Mistral Large 3 with other leading models using the same data and benchmark logic.
View the complete LLM comparison