Head-to-head comparison
GPT-5.4 vs. MiMo-V2.5-Pro
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
106
shared result series
13
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 | MiMo-V2.5-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Released | Mar 2026 | Apr 23, 2026 |
| Availability | Active | Open Source |
| Model type | Proprietary | Open Weights |
| Parameters | Not published | 1T, 42B active |
| Architecture | Not published | Mixture of Experts |
| Context window | 1,050,000 tokens | 1,000,000 tokens |
| Knowledge cutoff | August 31, 2025 | Not published |
| Technical sources | Model | Model |
| API pricing per 1M tokens | ||
| API input | $2.5 ≤272K / $5 >272K | $0.43 |
| API output | $15 ≤272K / $22.5 >272K | $0.87 |
| Cache read | $0.25 ≤272K / $0.5 >272K | $0. |
| Cache write (5 min.) | Not listed | Not listed |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 07/30/2026Source | 07/31/2026Source |
GPT-5.4MiMo-V2.5-Pro
API inputUSD per 1M tokens, base tier
GPT-5.4$2.5
MiMo-V2.5-Pro$0.435Lower price
API outputUSD per 1M tokens, base tier
GPT-5.4$15
MiMo-V2.5-Pro$0.87Lower price
Cache readUSD per 1M tokens, base tier
GPT-5.4$0.25
MiMo-V2.5-Pro$0.004Lower 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.
106 shared result series
GPT-5.4MiMo-V2.5-Pro
Arena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.41,465.439 arena points
MiMo-V2.5-Pro1,467.876 arena pointsNo clear lead
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.434.984 %Winner
MiMo-V2.5-Pro21.557 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.465.268 %Winner
MiMo-V2.5-Pro61.422 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.491.666 %Winner
MiMo-V2.5-Pro82.576 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.40 %
MiMo-V2.5-Pro2.083 %Winner
LegalBenchOverall. Higher is better. No documented setup difference
GPT-5.486.044 %Winner
MiMo-V2.5-Pro77.129 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GPT-5.484.141 %Winner
MiMo-V2.5-Pro81.354 %
MedCodeOverall. Higher is better. No documented setup difference
GPT-5.441.292 %Winner
MiMo-V2.5-Pro32.484 %
MedScribeOverall. Higher is better. No documented setup difference
GPT-5.477.549 %
MiMo-V2.5-Pro83.73 %Winner
MMLU-ProOverall. Higher is better. No documented setup difference
GPT-5.487.482 %Winner
MiMo-V2.5-Pro84.595 %
SWE-bench VerifiedOverall. Higher is better. No documented setup difference
GPT-5.478.2 %Winner
MiMo-V2.5-Pro74 %
TaxEval v2Overall. Higher is better. No documented setup difference
GPT-5.473.958 %Winner
MiMo-V2.5-Pro73.794 %
| Benchmark and task | GPT-5.4 | MiMo-V2.5-Pro | Comparability | Source |
|---|---|---|---|---|
| Arena Text, Style ControlOverall | 1,465.439 arena points 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. | 1,467.876 arena pointsNo clear lead 95% confidence interval: ±4.128The 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 differenceNo clear leadGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 63,759 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 50,613 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationOverall | 34.984 %Winner | 21.557 % | 1accuracyHigher is betterCohort: vals-code-migration:1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-code-migration-2026-08-16-107652dc6bfcRetrieved 2026-08-16 |
| CorpFin v2Overall | 65.268 %Winner | 61.422 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-corp_fin_v2-2026-08-16-45bbf84f57abRetrieved 2026-08-16 |
| GPQA DiamondOverall | 91.666 %Winner | 82.576 % | 1accuracyHigher is betterCohort: vals-gpqa:1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-gpqa-2026-08-16-7f8363eaa2dbRetrieved 2026-08-16 |
| Harvey's Legal Agent BenchmarkOverall · Task fully resolved | 0 % | 2.083 %Winner | 1task resolution rateHigher is betterCohort: vals-legal-agent-benchmark:1:overallNo documented setup differenceWinner: MiMo-V2.5-ProGPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-hlab-2026-08-16-bae90566df2fRetrieved 2026-08-16 |
| LegalBenchOverall | 86.044 %Winner | 77.129 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-legal_bench-2026-08-16-d5b3b1b2b5c8Retrieved 2026-08-16 |
| LiveCodeBench v6Overall | 84.141 %Winner | 81.354 % | 1accuracyHigher is betterCohort: vals-lcb:1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-lcb-2026-08-16-17b9c147080dRetrieved 2026-08-16 |
| MedCodeOverall | 41.292 %Winner | 32.484 % | 1accuracyHigher is betterCohort: vals-medcode:1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medcode-2026-08-16-524f7f474eacRetrieved 2026-08-16 |
| MedScribeOverall | 77.549 % | 83.73 %Winner | 1accuracyHigher is betterCohort: vals-medscribe:1:overallNo documented setup differenceWinner: MiMo-V2.5-ProGPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medscribe-2026-08-16-c385354a7e62Retrieved 2026-08-16 |
| MMLU-ProOverall | 87.482 %Winner | 84.595 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-mmlu_pro-2026-08-16-e14d5bb3a34cRetrieved 2026-08-16 |
| SWE-bench VerifiedOverall | 78.2 %Winner | 74 % | 1accuracyHigher is betterCohort: vals-swebench:1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-swebench-2026-08-16-c133071b8167Retrieved 2026-08-16 |
| TaxEval v2Overall | 73.958 %Winner | 73.794 % | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05 MiMo-V2.5-Pro: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-tax_eval_v2-2026-08-16-5bbd495dac53Retrieved 2026-08-16 |
| Vibe Code Bench v1.1Overall | 67.421 %Winner | 34.113 % | 1.1accuracyHigher is betterCohort: vals-vibe-code-bench:1.1:overallNo documented setup differenceWinner: GPT-5.4GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Harness: OpenHands MiMo-V2.5-Pro: Harness: OpenHands | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-vibe-code-2026-08-16-a73c9770bcc4Retrieved 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. | 1,467.876 arena points 95% confidence interval: ±4.128The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 60,819 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 50,613 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationCLI | 23.788 %Higher measured value | 13.981 % | 1accuracyHigher is betterCohort: vals-code-migration:1:cliTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-code-migration-2026-08-11-3a2d5ce718a3Retrieved 2026-08-11 |
| CorpFin v2Exact Pages | 64.103 %Higher measured value | 60.373 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:exact_pagesTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-corp_fin_v2-2026-08-11-d9e58d191cd9Retrieved 2026-08-11 |
| GPQA DiamondFew-Shot CoT | 91.414 %Higher measured value | 80.808 % | 1accuracyHigher is betterCohort: vals-gpqa:1:diamond_few_shot_cotTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-gpqa-2026-08-11-d3325290a404Retrieved 2026-08-11 |
| LegalBenchConclusion Tasks | 88.939 %Higher measured value | 88.031 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:conclusion_tasksTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-legal_bench-2026-08-11-836e5e44618eRetrieved 2026-08-11 |
| LiveCodeBench v6Easy | 99.068 %No direct winner | 99.068 %No direct winner | 1accuracyHigher is betterCohort: vals-lcb:1:easyTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-lcb-2026-08-11-0342bcc364e4Retrieved 2026-08-11 |
| MMLU-ProBiology | 92.887 %Higher measured value | 92.469 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:biologyTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| SWE-bench Verified<15 min fix | 88.144 %Higher measured value | 82.474 % | 1accuracyHigher is betterCohort: vals-swebench:1:<15 min fixTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-08Import ID: vals-swebench-2026-08-11-a6212cd857d8Retrieved 2026-08-11 |
| TaxEval v2Correctness | 64.922 %Higher measured value | 63.123 % | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:correctnessTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-tax_eval_v2-2026-08-11-d05a40bf446fRetrieved 2026-08-11 |
| Arena Text, Style ControlBusiness, management and finance | 1,474.218 arena pointsNo clear lead 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. | 1,470.913 arena points 95% confidence interval: ±7.118The 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 differenceNo clear leadGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,072 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 10,018 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationCOBOL | 68.571 %Higher measured value | 44.286 % | 1accuracyHigher is betterCohort: vals-code-migration:1:cobolTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-code-migration-2026-08-11-3a2d5ce718a3Retrieved 2026-08-11 |
| CorpFin v2Max Fitting Context | 64.918 %Higher measured value | 61.422 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:max_fitting_contextTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-corp_fin_v2-2026-08-11-d9e58d191cd9Retrieved 2026-08-11 |
| GPQA DiamondZero-Shot CoT | 91.919 %Higher measured value | 84.343 % | 1accuracyHigher is betterCohort: vals-gpqa:1:diamond_zero_shot_cotTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-gpqa-2026-08-11-d3325290a404Retrieved 2026-08-11 |
| LegalBenchInterpretation Tasks | 83.921 %Higher measured value | 79.497 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:interpretation_tasksTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-legal_bench-2026-08-11-836e5e44618eRetrieved 2026-08-11 |
| LiveCodeBench v6Hard | 67.714 %Higher measured value | 58.571 % | 1accuracyHigher is betterCohort: vals-lcb:1:hardTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-lcb-2026-08-11-0342bcc364e4Retrieved 2026-08-11 |
| MMLU-ProBusiness | 91.762 %Higher measured value | 89.987 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:businessTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| SWE-bench Verified>4 hours | 0 % | 33.333 %Higher measured value | 1accuracyHigher is betterCohort: vals-swebench:1:>4 hoursTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-08Import ID: vals-swebench-2026-08-11-a6212cd857d8Retrieved 2026-08-11 |
| TaxEval v2Stepwise Reasoning | 82.993 % | 84.464 %Higher measured value | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:stepwise_reasoningTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-tax_eval_v2-2026-08-11-d05a40bf446fRetrieved 2026-08-11 |
| 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. | 1,470.913 arena points 95% confidence interval: ±7.118The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,373 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 10,018 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationCode Quality | 3.632 / 5Higher measured value | 3.382 / 5 | 1mean reviewer code-quality ratingHigher is betterCohort: vals-code-migration:1:code_qualityTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-code-migration-2026-08-11-3a2d5ce718a3Retrieved 2026-08-11 |
| CorpFin v2Shared Max Context | 66.783 %Higher measured value | 62.471 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:shared_max_contextTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-corp_fin_v2-2026-08-11-d9e58d191cd9Retrieved 2026-08-11 |
| LegalBenchIssue Tasks | 90.526 %Higher measured value | 80.173 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:issue_tasksTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-legal_bench-2026-08-11-836e5e44618eRetrieved 2026-08-11 |
| LiveCodeBench v6Medium | 85.64 % | 86.423 %Higher measured value | 1accuracyHigher is betterCohort: vals-lcb:1:mediumTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-lcb-2026-08-11-0342bcc364e4Retrieved 2026-08-11 |
| MMLU-ProChemistry | 91.078 %Higher measured value | 90.459 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:chemistryTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| SWE-bench Verified1-4 hours | 50 %Higher measured value | 33.333 % | 1accuracyHigher is betterCohort: vals-swebench:1:1-4 hoursTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-08Import ID: vals-swebench-2026-08-11-a6212cd857d8Retrieved 2026-08-11 |
| Arena Text, Style ControlChinese | 1,496.688 arena points 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. | 1,511.817 arena pointsNo clear lead 95% confidence interval: ±12.271The 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 differenceNo clear leadGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,574 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 2,736 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| LegalBenchRhetoric Tasks | 82.824 %Higher measured value | 64.964 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:rhetoric_tasksTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-legal_bench-2026-08-11-836e5e44618eRetrieved 2026-08-11 |
| MMLU-ProComputer Science | 89.756 %Higher measured value | 88.049 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:computer_scienceTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| SWE-bench Verified15 min - 1 hour | 76.245 %Higher measured value | 74.713 % | 1accuracyHigher is betterCohort: vals-swebench:1:15 min - 1 hourTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-08Import ID: vals-swebench-2026-08-11-a6212cd857d8Retrieved 2026-08-11 |
| Arena Text, Style ControlChinese | 1,506.007 arena points 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. | 1,511.817 arena pointsHigher measured value 95% confidence interval: ±12.271The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,369 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 2,736 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| LegalBenchRule Tasks | 84.008 %Higher measured value | 72.98 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:rule_tasksTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-legal_bench-2026-08-11-836e5e44618eRetrieved 2026-08-11 |
| MMLU-ProEconomics | 89.692 %Higher measured value | 87.915 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:economicsTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| Arena Text, Style ControlCoding | 1,513.75 arena points 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. | 1,520.126 arena pointsNo clear lead 95% confidence interval: ±6.518The 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 differenceNo clear leadGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 17,752 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 13,962 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProEngineering | 85.243 %Higher measured value | 81.115 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:engineeringTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| 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. | 1,520.126 arena points 95% confidence interval: ±6.518The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 16,515 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 13,962 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProHealth | 82.396 %Higher measured value | 79.218 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:healthTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| Arena Text, Style ControlCreative writing | 1,436.291 arena pointsNo clear lead 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. | 1,433.675 arena points 95% confidence interval: ±7.575The 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 differenceNo clear leadGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,314 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 8,652 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProHistory | 79.265 %Higher measured value | 76.64 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:historyTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| 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. | 1,433.675 arena points 95% confidence interval: ±7.575The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,119 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 8,652 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProLaw | 75.477 %Higher measured value | 66.939 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:lawTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| Arena Text, Style ControlEnglish | 1,468.758 arena points 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. | 1,482.21 arena pointsWinner 95% confidence interval: ±5.356The 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: MiMo-V2.5-ProGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 29,658 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 22,059 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProMath | 94.671 %Higher measured value | 93.634 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:mathTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| Arena Text, Style ControlEnglish | 1,478.413 arena points 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. | 1,482.21 arena pointsHigher measured value 95% confidence interval: ±5.356The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 28,120 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 22,059 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProOthers | 86.472 %Higher measured value | 80.628 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:otherTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| Arena Text, Style ControlEntertainment, sports and media | 1,433.639 arena points 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. | 1,437.359 arena pointsNo clear lead 95% confidence interval: ±6.985The 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 differenceNo clear leadGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,629 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 11,124 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProPhilosophy | 86.974 %Higher measured value | 79.96 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:philosophyTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| 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. | 1,437.359 arena points 95% confidence interval: ±6.985The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,966 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 11,124 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProPhysics | 91.224 %No direct winner | 91.224 %No direct winner | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:physicsTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| Arena Text, Style ControlExcluding ties | 1,471.723 arena points 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. | 1,473.091 arena pointsNo clear lead 95% confidence interval: ±5.304The 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 differenceNo clear leadGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 48,930 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 38,559 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| MMLU-ProPsychology | 87.845 %Higher measured value | 86.09 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:psychologyTest setup not documented as identicalNo direct winnerGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5-Pro: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| 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. | 1,473.091 arena points 95% confidence interval: ±5.304The 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 MiMo-V2.5-Pro: Snapshot: mimo-v2.5-pro, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 46,537 anonymous pairwise votes.MiMo-V2.5-Pro: Style-controlled Arena rating from 38,559 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
The table shows 64 diversified result series from 106 shared results. This prevents one benchmark with many subtasks from crowding out every other test.
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 MiMo-V2.5-Pro with other leading models using the same data and benchmark logic.
View the complete LLM comparison