Head-to-head comparison
Claude Opus 5 vs. Claude Fable 5
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
233
shared result series
26
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 | Claude Opus 5 | Claude Fable 5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Released | Jul 24, 2026 | Jun 9, 2026 |
| Availability | Active | Active |
| Model type | Proprietary | Proprietary |
| Parameters | Not published | Not published |
| Architecture | Not published | Not published |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Knowledge cutoff | May 2026 | January 2026 |
| Technical sources | Model, Knowledge cutoff | Model, Context, Knowledge cutoff |
| API pricing per 1M tokens | ||
| API input | $5 | $10 |
| API output | $25 | $50 |
| Cache read | $0.5 | $1 |
| Cache write (5 min.) | $6.25 | $12.5 |
| Cache write (1 hr.) | $10 | $20 |
| Price verified | 07/30/2026Source | 07/30/2026Source |
Claude Opus 5Claude Fable 5
API inputUSD per 1M tokens, base tier
Claude Opus 5$5Lower price
Claude Fable 5$10
API outputUSD per 1M tokens, base tier
Claude Opus 5$25Lower price
Claude Fable 5$50
Cache readUSD per 1M tokens, base tier
Claude Opus 5$0.5Lower price
Claude Fable 5$1
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.
233 shared result series
Claude Opus 5Claude Fable 5
Arena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
Claude Opus 51,493.745 arena points
Claude Fable 51,506.631 arena pointsHigher measured value
Code MigrationOverall. Higher is better. No documented setup difference
Claude Opus 557.473 %Winner
Claude Fable 555.065 %
CorpFin v2Overall. Higher is better. No documented setup difference
Claude Opus 573.194 %Winner
Claude Fable 571.834 %
EMBOverall. Higher is better. No documented setup difference
Claude Opus 573.556 %
Claude Fable 573.666 %Winner
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Claude Opus 558.633 %Winner
Claude Fable 556.314 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Claude Opus 593.434 %Winner
Claude Fable 593.182 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Claude Opus 56.667 %
Claude Fable 511.25 %Winner
IOIOverall. Higher is better. No documented setup difference
Claude Opus 591.667 %Winner
Claude Fable 572.25 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Claude Opus 555.288 %Winner
Claude Fable 549.519 %
LegalBenchOverall. Higher is better. No documented setup difference
Claude Opus 586.974 %
Claude Fable 588.561 %Winner
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Claude Opus 589.03 %
Claude Fable 589.78 %Winner
MedCodeOverall. Higher is better. No documented setup difference
Claude Opus 563.57 %Winner
Claude Fable 556.07 %
| Benchmark and task | Claude Opus 5 | Claude Fable 5 | Comparability | Source |
|---|---|---|---|---|
| Arena Text, Style ControlOverall | 1,493.745 arena points 95% confidence interval: ±5.332The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,506.631 arena pointsHigher measured value 95% confidence interval: ±5.427The 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 winnerClaude Opus 5: Snapshot: claude-opus-5-high, Reasoning: high, Harness: Arena text, style control Claude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style controlClaude Opus 5: Style-controlled Arena rating from 19,792 anonymous pairwise votes.Claude Fable 5: Style-controlled Arena rating from 21,439 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationOverall | 57.473 %Winner | 55.065 % | 1accuracyHigher is betterCohort: vals-code-migration:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: 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 | 73.194 %Winner | 71.834 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-corp_fin_v2-2026-08-16-45bbf84f57abRetrieved 2026-08-16 |
| EMBOverall | 73.556 % | 73.666 %Winner | 1accuracyHigher is betterCohort: vals-emb:1:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-emb-2026-08-16-68d5d1d47a97Retrieved 2026-08-16 |
| Finance Agent (v2)Overall | 58.633 %Winner | 56.314 % | 2accuracyHigher is betterCohort: vals-finance-agent-v2:2:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-fabv2-2026-08-16-8853da43085dRetrieved 2026-08-16 |
| GPQA DiamondOverall | 93.434 %Winner | 93.182 % | 1accuracyHigher is betterCohort: vals-gpqa:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: 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 | 6.667 % | 11.25 %Winner | 1task resolution rateHigher is betterCohort: vals-legal-agent-benchmark:1:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-hlab-2026-08-16-bae90566df2fRetrieved 2026-08-16 |
| IOIOverall | 91.667 %Winner | 72.25 % | 1accuracyHigher is betterCohort: vals-ioi:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-ioi-2026-08-16-d9164ef483aaRetrieved 2026-08-16 |
| Legal Research BenchOverall · All-pass | 55.288 %Winner | 49.519 % | 1all-pass rateHigher is betterCohort: vals-legal-research:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-legal_research-2026-08-16-af296c00ecaaRetrieved 2026-08-16 |
| LegalBenchOverall | 86.974 % | 88.561 %Winner | 1accuracyHigher is betterCohort: vals-legal-bench:1:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: No further settings disclosed Claude Fable 5: 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 | 89.03 % | 89.78 %Winner | v6pass@1Higher is betterCohort: vals-livecodebench-v6-2026-08-01No documented setup differenceWinner: Claude Fable 5Claude Opus 5: Attempts: pass@1 Claude Fable 5: Attempts: pass@1More than 1,000 bounded Python tasks. | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-01Import ID: curated-vals-ai-2026-08-02-85443f94ecaf / curated-vals-ai-2026-08-02-379e22bc59ecRetrieved 2026-08-02 |
| MedCodeOverall | 63.57 %Winner | 56.07 % | 1accuracyHigher is betterCohort: vals-medcode:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medcode-2026-08-16-524f7f474eacRetrieved 2026-08-16 |
| MedScribeOverall | 90.985 %Winner | 88.522 % | 1accuracyHigher is betterCohort: vals-medscribe:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medscribe-2026-08-16-c385354a7e62Retrieved 2026-08-16 |
| MMLU-ProOverall | 91.59 %Winner One question fell back to Opus 4.8. Counting it as wrong changes the Vals result from 91.591% to 91.582%. | 91.5 % | ProaccuracyHigher is betterCohort: vals-mmlu-pro-5-shot-cot-2026-08-01No documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed12,032 questions across 14 subjects with five examples and chain of thought. | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-01Import ID: curated-vals-ai-2026-08-02-38436da8b639 / curated-vals-ai-2026-08-02-ee2f79b83f82Retrieved 2026-08-02 |
| MMMU-ProOverall | 89.88 %Winner | 89.31 % | ProaccuracyHigher is betterCohort: vals-mmmu-pro-pass1-temp0-2026-07-31No documented setup differenceWinner: Claude Opus 5Claude Opus 5: Attempts: pass@1 Claude Fable 5: Attempts: pass@1Approximately 1,700 multimodal tasks, Pass@1 at temperature 0. | Vals AIType: Independent evaluationLeaderboard updated: 2026-07-31Import ID: curated-vals-ai-2026-08-02-7cb2c9e11cfa / curated-vals-ai-2026-08-02-7494d00241b9Retrieved 2026-08-02 |
| MortgageTaxOverall | 72.059 %Winner | 68.919 % | 1accuracyHigher is betterCohort: vals-mortgage-tax:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-mortgage_tax-2026-08-16-e78c985dbb1cRetrieved 2026-08-16 |
| ProgramBenchOverall | 3 %Winner | 2 % | 1accuracyHigher is betterCohort: vals-programbench:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-programbench-2026-08-16-08d9727662ddRetrieved 2026-08-16 |
| ProofBenchOverall | 78 %Winner | 77 % | currentsolved proofsHigher is betterCohort: vals-proofbench-lean4-40-steps-2026-07-31No documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed200 Lean 4 problems with tool access and up to 40 steps. | Vals AIType: Independent evaluationLeaderboard updated: 2026-07-31Import ID: curated-vals-ai-2026-08-02-0c2bc33f9e1f / curated-vals-ai-2026-08-02-45b5a9779826Retrieved 2026-08-02 |
| Public Benefits Bench v1.1Overall | 76.928 %Winner | 70.433 % | 1.1accuracyHigher is betterCohort: vals-snap:1.1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-public-benefits-bench-2026-08-16-7ce68123c502Retrieved 2026-08-16 |
| SAGEOverall | 49.426 % | 51.89 %Winner | 1accuracyHigher is betterCohort: vals-sage:1:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-sage-2026-08-16-a416dd25affbRetrieved 2026-08-16 |
| SWE-bench VerifiedOverall | 97 %Winner Editorial selection from the Vals AI table, not a complete extract of the comparison cohort. | 95 % Editorial selection from the Vals AI table, not a complete extract of the comparison cohort. | VerifiedresolvedHigher is betterCohort: swe-verified-vals-mini-swe-agent-2026-07-31No documented setup differenceWinner: Claude Opus 5Claude Opus 5: Agent: mini-SWE-agent, Harness: mini-SWE-agent Claude Fable 5: Agent: mini-SWE-agent, Harness: mini-SWE-agentShared mini-SWE-agent harness with bash tools. | Vals AIType: Independent evaluationLeaderboard updated: 2026-07-31Import ID: curated-vals-ai-2026-08-01-6d188ba56b5b / curated-vals-ai-2026-08-01-610b342edea8Retrieved 2026-08-01 |
| TaxEval v2Overall | 75.143 % | 76.942 %Winner | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-tax_eval_v2-2026-08-16-5bbd495dac53Retrieved 2026-08-16 |
| Terminal-Bench 2.1Overall | 84.64 %Winner Nine passing tasks used an Opus 4.8 fallback because of safety systems. Counting them as failures lowers the Vals result to 81.27%. | 80.52 % Safety systems can cause individual Fable 5 calls to fall back to Opus 4.8. | 2.1pass@1Higher is betterCohort: vals-terminal-bench-2-1-terminus2-2026-08-01No documented setup differenceWinner: Claude Opus 5Claude Opus 5: Agent: Terminus 2, Harness: Terminus 2, Attempts: pass@1 Claude Fable 5: Agent: Terminus 2, Harness: Terminus 2, Attempts: pass@1Constant Terminus 2 agent, 89 tasks, Daytona environments, and a shared time limit. | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-01Import ID: curated-vals-ai-2026-08-02-52c225d36f55 / curated-vals-ai-2026-08-02-40d23466bc74Retrieved 2026-08-02 |
| Vals IndexOverall | 67.213 %Winner | 66.036 % | 2weighted index scoreHigher is betterCohort: vals-vals-index:2:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-vals_index-2026-08-16-ab641d89d6edRetrieved 2026-08-16 |
| Vals Multimodal IndexOverall | 73.896 % | 74.154 %Winner | 1.2weighted index scoreHigher is betterCohort: vals-vals-multimodal-index:1.2:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-11Import ID: vals-vals_multimodal_index-2026-08-16-9f3ebb221408Retrieved 2026-08-16 |
| Vibe Code Bench v1.1Overall | 88.404 % | 90.352 %Winner | 1.1accuracyHigher is betterCohort: vals-vibe-code-bench:1.1:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: Harness: OpenHands Claude Fable 5: 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 | 1,491.094 arena points 95% confidence interval: ±6.993The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,506.631 arena pointsHigher measured value 95% confidence interval: ±5.427The 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 winnerClaude Opus 5: Snapshot: claude-opus-5-max, Reasoning: max, Harness: Arena text, style control Claude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style controlClaude Opus 5: Style-controlled Arena rating from 9,559 anonymous pairwise votes.Claude Fable 5: Style-controlled Arena rating from 21,439 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationCLI | 53.297 % | 60.087 %Higher measured value | 1accuracyHigher is betterCohort: vals-code-migration:1:cliTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 | 68.648 %Higher measured value | 66.9 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:exact_pagesTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 |
| EMBComps | 75.171 %Higher measured value | 70.785 % | 1accuracyHigher is betterCohort: vals-emb:1:compsTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-emb-2026-08-11-e3c855e236e4Retrieved 2026-08-11 |
| Finance Agent (v2)Adjustments | 54.617 %Winner | 51.092 % | 2accuracyHigher is betterCohort: vals-finance-agent-v2:2:adjustmentsNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-fabv2-2026-08-11-3e5c93a1857cRetrieved 2026-08-11 |
| GPQA DiamondFew-Shot CoT | 92.424 % | 92.929 %Higher measured value | 1accuracyHigher is betterCohort: vals-gpqa:1:diamond_few_shot_cotTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-gpqa-2026-08-11-d3325290a404Retrieved 2026-08-11 |
| Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed | 87.319 % | 92.035 %Higher measured value | 1criteria pass rateHigher is betterCohort: vals-legal-agent-benchmark:1:criteria_pass_rate__antitrust_competitionTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-07Import ID: vals-hlab-2026-08-11-ea11b6e53414Retrieved 2026-08-11 |
| IOIIOI 2024 | 100 %Tie | 100 %Tie | 1accuracyHigher is betterCohort: vals-ioi:1:ioi2024No documented setup differenceTieClaude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-ioi-2026-08-11-2dfe8b4b8b7bRetrieved 2026-08-11 |
| Legal Research BenchAdministrative / Regulatory · All-pass | 65.152 %Higher measured value | 57.576 % | 1all-pass rateHigher is betterCohort: vals-legal-research:1:administrative_regulatoryTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-legal_research-2026-08-11-326cf7aaca58Retrieved 2026-08-11 |
| LegalBenchConclusion Tasks | 91.56 % | 91.775 %Higher measured value | 1accuracyHigher is betterCohort: vals-legal-bench:1:conclusion_tasksTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 v6Overall | 89.033 % | 89.778 %Winner | 1accuracyHigher is betterCohort: vals-lcb:1:overallNo documented setup differenceWinner: Claude Fable 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-lcb-2026-08-16-17b9c147080dRetrieved 2026-08-16 |
| MMLU-ProOverall | 91.591 %Winner | 91.502 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-mmlu_pro-2026-08-16-e14d5bb3a34cRetrieved 2026-08-16 |
| MMMU-ProOverall | 89.884 %Winner | 89.306 % | 1accuracyHigher is betterCohort: vals-mmmu:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmmu-2026-08-16-37c9a8c7e21fRetrieved 2026-08-16 |
| MortgageTaxNumerical Extraction | 81.399 %Higher measured value | 76.709 % | 1accuracyHigher is betterCohort: vals-mortgage-tax:1:numerical_extractionTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mortgage_tax-2026-08-11-5ea6eef3e482Retrieved 2026-08-11 |
| ProgramBenchAlmost Resolved | 41.5 %Higher measured value | 33 % | 1accuracyHigher is betterCohort: vals-programbench:1:almostTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-programbench-2026-08-11-b6f8959fbdfeRetrieved 2026-08-11 |
| ProofBenchOverall | 99 %Winner | 95 % | 1.1accuracyHigher is betterCohort: vals-proof-bench:1.1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-proof_bench-2026-08-16-14232db24de1Retrieved 2026-08-16 |
| SAGEAutomata | 32.54 % | 39.682 %Higher measured value | 1accuracyHigher is betterCohort: vals-sage:1:automataTest setup not documented as identicalNo direct winnerClaude Opus 5: Temperature: 1, Output limit: 30,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-sage-2026-08-11-f1f79f6d8af3Retrieved 2026-08-11 |
| SWE-bench VerifiedOverall | 97 %Winner | 95 % | 1accuracyHigher is betterCohort: vals-swebench:1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-swebench-2026-08-16-c133071b8167Retrieved 2026-08-16 |
| TaxEval v2Correctness | 61.979 % | 65.822 %Higher measured value | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:correctnessTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 |
| Terminal-Bench 2.1Overall | 84.644 %Winner | 80.524 % | 2.1accuracyHigher is betterCohort: vals-terminal-bench-2-1:2.1:overallNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: No further settings disclosed Claude Fable 5: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-terminal-bench-2-1-2026-08-16-b3f38c18bea4Retrieved 2026-08-16 |
| Vals IndexCorpFin v2 | 74.942 %Higher measured value | 71.562 % | 1.2benchmark scoreHigher is betterCohort: vals-vals-index:1.2:corp_fin_v2Test setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-vals_index-2026-08-11-e79d08d59249Retrieved 2026-08-11 |
| Vals Multimodal IndexCorpFin v2 | 74.942 %Higher measured value | 71.562 % | 1.2benchmark scoreHigher is betterCohort: vals-vals-multimodal-index:1.2:corp_fin_v2Test setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-vals_multimodal_index-2026-08-11-fa704862df19Retrieved 2026-08-11 |
| Arena Text, Style ControlBusiness, management and finance | 1,488.821 arena points 95% confidence interval: ±10.372The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,502.177 arena pointsHigher measured value 95% confidence interval: ±9.475The 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 winnerClaude Opus 5: Snapshot: claude-opus-5-high, Reasoning: high, Harness: Arena text, style control Claude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style controlClaude Opus 5: Style-controlled Arena rating from 3,811 anonymous pairwise votes.Claude Fable 5: Style-controlled Arena rating from 4,464 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationCOBOL | 70 %Higher measured value | 40 % | 1accuracyHigher is betterCohort: vals-code-migration:1:cobolTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 | 75.991 % | 77.04 %Higher measured value | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:max_fitting_contextTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 |
| EMBDataroom | 87.681 %Higher measured value | 85.362 % | 1accuracyHigher is betterCohort: vals-emb:1:dataroomTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-emb-2026-08-11-e3c855e236e4Retrieved 2026-08-11 |
| Finance Agent (v2)All-Pass | 47.708 %Winner | 45.694 % | 2accuracyHigher is betterCohort: vals-finance-agent-v2:2:all_passNo documented setup differenceWinner: Claude Opus 5Claude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-fabv2-2026-08-11-3e5c93a1857cRetrieved 2026-08-11 |
| GPQA DiamondZero-Shot CoT | 94.444 %Higher measured value | 93.434 % | 1accuracyHigher is betterCohort: vals-gpqa:1:diamond_zero_shot_cotTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-gpqa-2026-08-11-d3325290a404Retrieved 2026-08-11 |
| Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved | 0 %No direct winner | 0 %No direct winner | 1task resolution rateHigher is betterCohort: vals-legal-agent-benchmark:1:antitrust_competitionTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-07Import ID: vals-hlab-2026-08-11-ea11b6e53414Retrieved 2026-08-11 |
| IOIIOI 2025 | 83.333 %Winner | 44.5 % | 1accuracyHigher is betterCohort: vals-ioi:1:ioi2025No documented setup differenceWinner: Claude Opus 5Claude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-ioi-2026-08-11-2dfe8b4b8b7bRetrieved 2026-08-11 |
| Legal Research BenchAdministrative / Regulatory · Weighted partial credit | 92.676 %Higher measured value | 90.224 % | 1weighted partial-credit scoreHigher is betterCohort: vals-legal-research:1:weighted_pass__administrative_regulatoryTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-legal_research-2026-08-11-326cf7aaca58Retrieved 2026-08-11 |
| LegalBenchInterpretation Tasks | 85.84 % | 86.863 %Higher measured value | 1accuracyHigher is betterCohort: vals-legal-bench:1:interpretation_tasksTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 %Higher measured value | 98.758 % | 1accuracyHigher is betterCohort: vals-lcb:1:easyTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, 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 | 95.676 %Higher measured value | 93.584 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:biologyTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| MortgageTaxSemantic Extraction | 62.719 %Higher measured value | 61.129 % | 1accuracyHigher is betterCohort: vals-mortgage-tax:1:semantic_extractionTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mortgage_tax-2026-08-11-5ea6eef3e482Retrieved 2026-08-11 |
| ProgramBenchFully Resolved | 3 %Higher measured value | 2 % | 1accuracyHigher is betterCohort: vals-programbench:1:strictTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-programbench-2026-08-11-b6f8959fbdfeRetrieved 2026-08-11 |
| SAGELinear Algebra | 76.056 %Higher measured value | 71.544 % | 1accuracyHigher is betterCohort: vals-sage:1:linear_algebraTest setup not documented as identicalNo direct winnerClaude Opus 5: Temperature: 1, Output limit: 30,000 tokens Claude Fable 5: Compute: max, Temperature: 1, Output limit: 30,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-sage-2026-08-11-f1f79f6d8af3Retrieved 2026-08-11 |
| SWE-bench Verified<15 min fix | 98.454 %Higher measured value | 95.876 % | 1accuracyHigher is betterCohort: vals-swebench:1:<15 min fixTest setup not documented as identicalNo direct winnerClaude Opus 5: No further settings disclosed Claude Fable 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-08Import ID: vals-swebench-2026-08-11-a6212cd857d8Retrieved 2026-08-11 |
The table shows 64 diversified result series from 233 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.