| Claude Haiku 5.5 (xhigh) | CursorBench 4.0 | 44.3% | cursor.com for Claude Haiku 5.5 (xhigh) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Haiku 5.5 on CursorBench 4.0 | 20018 |
| Claude Haiku 5.5 (medium) | CursorBench 4.0 | 36.9% | cursor.com for Claude Haiku 5.5 (medium) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Haiku 5.5 on CursorBench 4.0 | 20018 |
| Claude Haiku 5.5 | FrontierSWE 2 — October 2026 evaluation | 43.8% | frontierswe.com for Claude Haiku 5.5 on FrontierSWE 2 — October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)FrontierSWE ScoreReported Benchmark leaderboardProximalIndependentRecord for Claude Haiku 5.5 on FrontierSWE 2 — October 2026 evaluation | 20018 |
| Claude Haiku 5.5 (high) | CursorBench 4.0 | 42.3% | cursor.com for Claude Haiku 5.5 (high) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Haiku 5.5 on CursorBench 4.0 | 20018 |
| Claude Haiku 5.5 (low) | CursorBench 4.0 | 30.9% | cursor.com for Claude Haiku 5.5 (low) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Haiku 5.5 on CursorBench 4.0 | 20018 |
| Claude Haiku 5.5 (max) | CursorBench 4.0 | 48.4% | cursor.com for Claude Haiku 5.5 (max) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Haiku 5.5 on CursorBench 4.0 | 20018 |
| Claude 3.7 Sonnet | GPQA Diamond — Epoch AI harness | 66.0% | epoch.ai for Claude 3.7 Sonnet on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude 3.7 Sonnet on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness | 20001 |
| Claude 3.7 Sonnet (Thinking) | Humanity's Last Exam Text only — Scale AI evaluation | 7.9% | labs.scale.com for Claude 3.7 Sonnet (Thinking) on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Claude 3.7 Sonnet on Humanity's Last Exam Text only — Scale AI evaluation | 20001 |
| Claude 3.7 Sonnet | SWE-bench Verified — Epoch AI harness | 61.0% | epoch.ai for Claude 3.7 Sonnet on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude 3.7 Sonnet on SWE-bench Verified — Epoch AI harness | 20001 |
| Claude Opus 4 | Humanity's Last Exam Text only — Scale AI evaluation | 6.3% | labs.scale.com for Claude Opus 4 on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Claude Opus 4 on Humanity's Last Exam Text only — Scale AI evaluation | 20002 |
| Claude Opus 4 | GPQA Diamond — Epoch AI harness | 69.2% | epoch.ai for Claude Opus 4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness | 20002 |
| Claude Opus 4 | SWE-bench Verified — Epoch AI harness | 70.7% | epoch.ai for Claude Opus 4 on SWE-bench Verified — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 4 on SWE-bench Verified — Epoch AI harness | 20002 |
| Claude Opus 4 (Thinking) | Humanity's Last Exam Text only — Scale AI evaluation | 10.8% | labs.scale.com for Claude Opus 4 (Thinking) on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Claude Opus 4 on Humanity's Last Exam Text only — Scale AI evaluation | 20002 |
| Claude Sonnet 4 | SWE-bench Pro Private — Scale AI SWE-Agent | 9.1% | labs.scale.com for Claude Sonnet 4 on SWE-bench Pro Private — Scale AI SWE-Agent (opens in a new tab)Archived copy (opens in a new tab)Public tasks resolvedReported Benchmark leaderboardScale AIIndependentRecord for Claude Sonnet 4 on SWE-bench Pro Private — Scale AI SWE-Agent | 20003 |
| Claude Sonnet 4 | GPQA Diamond — Epoch AI harness | 66.7% | epoch.ai for Claude Sonnet 4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Sonnet 4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness | 20003 |
| Claude Sonnet 4 (Thinking) | Humanity's Last Exam Text only — Scale AI evaluation | 7.6% | labs.scale.com for Claude Sonnet 4 (Thinking) on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Claude Sonnet 4 on Humanity's Last Exam Text only — Scale AI evaluation | 20003 |
| Claude Sonnet 4 | Humanity's Last Exam Text only — Scale AI evaluation | 5.4% | labs.scale.com for Claude Sonnet 4 on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Claude Sonnet 4 on Humanity's Last Exam Text only — Scale AI evaluation | 20003 |
| Claude Sonnet 4 | SWE-bench Pro Public — Scale AI SWE-Agent | 42.7% | labs.scale.com for Claude Sonnet 4 on SWE-bench Pro Public — Scale AI SWE-Agent (opens in a new tab)Archived copy (opens in a new tab)Public tasks resolvedReported Benchmark leaderboardScale AIIndependentRecord for Claude Sonnet 4 on SWE-bench Pro Public — Scale AI SWE-Agent | 20003 |
| Claude Fable 5.1 (high) | CharXiv Descriptive and reasoning — Mercor single-shot | 94.1% | mercor.com for Claude Fable 5.1 (high) on CharXiv Descriptive and reasoning — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)CharXiv AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on CharXiv Descriptive and reasoning — Mercor single-shot | 20004 |
| Claude Fable 5.1 (xhigh) | CursorBench 4.0 | 51.6% | cursor.com for Claude Fable 5.1 (xhigh) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Fable 5.1 on CursorBench 4.0 | 20004 |
| Claude Fable 5.1 (max) | SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps | 43.3% | mercor.com for Claude Fable 5.1 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab)Archived copy (opens in a new tab)Mean pass@1Reported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps | 20004 |
| Claude Fable 5.1 (low) | CursorBench 4.0 | 45.1% | cursor.com for Claude Fable 5.1 (low) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Fable 5.1 on CursorBench 4.0 | 20004 |
| Claude Fable 5.1 (max) | MedXpertQA MM — Mercor single-shot | 83.7% | mercor.com for Claude Fable 5.1 (max) on MedXpertQA MM — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on MedXpertQA MM — Mercor single-shot | 20004 |
| Claude Fable 5.1 (max) | DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps | 64.9% | mercor.com for Claude Fable 5.1 (max) on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab)Archived copy (opens in a new tab)DeepSWE Pass@1Reported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps | 20004 |
| Claude Fable 5.1 (max) | AutomationBench 1.0.6 | 22.4% | zapier.com for Claude Fable 5.1 (max) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Claude Fable 5.1 on AutomationBench 1.0.6 | 20004 |
| Claude Fable 5.1 (max) | BrowseComp 130-question subset — Mercor web research agent | 85.2% | mercor.com for Claude Fable 5.1 (max) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab)Archived copy (opens in a new tab)BrowseComp AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on BrowseComp 130-question subset — Mercor web research agent | 20004 |
| Claude Fable 5.1 (xhigh) | AutomationBench 1.0.6 | 21.3% | zapier.com for Claude Fable 5.1 (xhigh) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Claude Fable 5.1 on AutomationBench 1.0.6 | 20004 |
| Claude Fable 5.1 (max) | CharXiv Descriptive and reasoning — Mercor single-shot | 95.1% | mercor.com for Claude Fable 5.1 (max) on CharXiv Descriptive and reasoning — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)CharXiv AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on CharXiv Descriptive and reasoning — Mercor single-shot | 20004 |
| Claude Fable 5.1 (high) | CWE-bench 1 — Claude Code | 58.0% | cwe-bench.com for Claude Fable 5.1 (high) on CWE-bench 1 — Claude Code (opens in a new tab)Archived copy (opens in a new tab)CWE-bench Programmatic Pass@1Reported Benchmark leaderboardCollinear AIIndependentRecord for Claude Fable 5.1 on CWE-bench 1 — Claude Code | 20004 |
| Claude Fable 5.1 (max) | Terminal-Bench 4.0 — Mercor mini-swe-agent | 53.0% | mercor.com for Claude Fable 5.1 (max) on Terminal-Bench 4.0 — Mercor mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on Terminal-Bench 4.0 — Mercor mini-swe-agent | 20004 |
| Claude Fable 5.1 (high) | SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps | 42.7% | mercor.com for Claude Fable 5.1 (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab)Archived copy (opens in a new tab)Mean pass@1Reported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps | 20004 |
| Claude Fable 5.1 (xHigh) | SWE Atlas Codebase QnA — Public; Claude Code | 60.0% | labs.scale.com for Claude Fable 5.1 (xHigh) on SWE Atlas Codebase QnA — Public; Claude Code (opens in a new tab)Archived copy (opens in a new tab)Mean pass@1Reported Benchmark leaderboardScale AIIndependentRecord for Claude Fable 5.1 on SWE Atlas Codebase QnA — Public; Claude Code | 20004 |
| Claude Fable 5.1 (high) | BrowseComp 130-question subset — Mercor web research agent | 78.3% | mercor.com for Claude Fable 5.1 (high) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab)Archived copy (opens in a new tab)BrowseComp AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on BrowseComp 130-question subset — Mercor web research agent | 20004 |
| Claude Fable 5.1 (max) | SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps | 91.1% | mercor.com for Claude Fable 5.1 (max) on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps | 20004 |
| Claude Fable 5.1 (high) | SWE-bench Verified — Mercor mini-swe-agent, 1000 steps | 92.1% | mercor.com for Claude Fable 5.1 (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps | 20004 |
| Claude Fable 5.1 (max) | SimpleQA Verified Original — Epoch AI harness | 70.8% | epoch.ai for Claude Fable 5.1 (max) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Fable 5.1 on SimpleQA Verified Original — Epoch AI harness | 20004 |
| Claude Fable 5.1 (high) | DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps | 67.3% | mercor.com for Claude Fable 5.1 (high) on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab)Archived copy (opens in a new tab)DeepSWE Pass@1Reported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps | 20004 |
| Claude Fable 5.1 (high) | MedXpertQA MM — Mercor single-shot | 79.7% | mercor.com for Claude Fable 5.1 (high) on MedXpertQA MM — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on MedXpertQA MM — Mercor single-shot | 20004 |
| Claude Fable 5.1 (high) | APEX-Agents Original | 59.7% | mercor.com for Claude Fable 5.1 (high) on APEX-Agents Original (opens in a new tab)Archived copy (opens in a new tab)Pass rateReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on APEX-Agents Original | 20004 |
| Claude Fable 5.1 | FrontierSWE 2 — October 2026 evaluation | 56.3% | frontierswe.com for Claude Fable 5.1 on FrontierSWE 2 — October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)FrontierSWE ScoreReported Benchmark leaderboardProximalIndependentRecord for Claude Fable 5.1 on FrontierSWE 2 — October 2026 evaluation | 20004 |
| Claude Fable 5.1 (max) | SWE-bench Verified — Mercor mini-swe-agent, 1000 steps | 96.6% | mercor.com for Claude Fable 5.1 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps | 20004 |
| Claude Fable 5.1 (max) | MMMU-Pro 1,730 questions — Mercor single-shot | 86.1% | mercor.com for Claude Fable 5.1 (max) on MMMU-Pro 1,730 questions — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)MMMU-Pro accuracySetting: Not statedReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on MMMU-Pro 1,730 questions — Mercor single-shot | 20004 |
| Claude Fable 5.1 (medium) | CursorBench 4.0 | 46.8% | cursor.com for Claude Fable 5.1 (medium) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Fable 5.1 on CursorBench 4.0 | 20004 |
| Claude Fable 5.1 (high) | CursorBench 4.0 | 49.2% | cursor.com for Claude Fable 5.1 (high) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Fable 5.1 on CursorBench 4.0 | 20004 |
| Claude Fable 5.1 (high) | Humanity's Last Exam Text only — Mercor single-shot | 53.1% | mercor.com for Claude Fable 5.1 (high) on Humanity's Last Exam Text only — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on Humanity's Last Exam Text only — Mercor single-shot | 20004 |
| Claude Fable 5.1 (max) | APEX-Agents Original | 68.6% | mercor.com for Claude Fable 5.1 (max) on APEX-Agents Original (opens in a new tab)Archived copy (opens in a new tab)Pass rateReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on APEX-Agents Original | 20004 |
| Claude Fable 5.1 (max) | MMLU-Pro Original — Mercor single-shot | 93.0% | mercor.com for Claude Fable 5.1 (max) on MMLU-Pro Original — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on MMLU-Pro Original — Mercor single-shot | 20004 |
| Claude Fable 5.1 (xhigh) | Humanity's Last Exam Text only — Scale AI evaluation | 46.8% | labs.scale.com for Claude Fable 5.1 (xhigh) on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardScale AIIndependentRecord for Claude Fable 5.1 on Humanity's Last Exam Text only — Scale AI evaluation | 20004 |
| Claude Fable 5.1 (max) | GPQA Diamond — Mercor single-shot | 91.4% | mercor.com for Claude Fable 5.1 (max) on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot | 20004 |
| Claude Fable 5.1 (max) | Humanity's Last Exam Text only — Mercor single-shot | 54.6% | mercor.com for Claude Fable 5.1 (max) on Humanity's Last Exam Text only — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Fable 5.1 on Humanity's Last Exam Text only — Mercor single-shot | 20004 |