APEX-Agents Original Effort: Medium 44.6% mercor.com for Claude Sonnet 5.5 (medium) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on APEX-Agents Original APEX-Agents Original Effort: Max 75.5% mercor.com for Claude Sonnet 5.5 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on APEX-Agents Original AutomationBench 1.0.6 Effort: Max 44.7% anthropic.com for Claude Sonnet 5.5 (max) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 28, 2026 System card Anthropic Self-reported Zapier AutomationBench Team Record for Claude Sonnet 5.5 on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: Max Configuration: Mercor web research agent, 100 steps, 3 hours 86.6% mercor.com for Claude Sonnet 5.5 (max) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab) Archived copy (opens in a new tab) BrowseComp Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on BrowseComp 130-question subset — Mercor web research agent CharXiv Descriptive and reasoning — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 96.1% mercor.com for Claude Sonnet 5.5 (max) on CharXiv Descriptive and reasoning — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) CharXiv Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on CharXiv Descriptive and reasoning — Mercor single-shot CursorBench 4.0 Effort: Low 35.8% cursor.com for Claude Sonnet 5.5 (low) on CursorBench 4.0 (opens in a new tab) CursorBench Accuracy Reported September 28, 2026 Benchmark leaderboard Cursor Independent Record for Claude Sonnet 5.5 on CursorBench 4.0 CursorBench 4.0 Effort: Medium 39.2% cursor.com for Claude Sonnet 5.5 (medium) on CursorBench 4.0 (opens in a new tab) CursorBench Accuracy Reported September 28, 2026 Benchmark leaderboard Cursor Independent Record for Claude Sonnet 5.5 on CursorBench 4.0 CursorBench 4.0 Effort: High 47.8% cursor.com for Claude Sonnet 5.5 (high) on CursorBench 4.0 (opens in a new tab) CursorBench Accuracy Reported September 28, 2026 Benchmark leaderboard Cursor Independent Record for Claude Sonnet 5.5 on CursorBench 4.0 CursorBench 4.0 Effort: xHigh 53.1% cursor.com for Claude Sonnet 5.5 (xhigh) on CursorBench 4.0 (opens in a new tab) CursorBench Accuracy Reported September 28, 2026 Benchmark leaderboard Cursor Independent Record for Claude Sonnet 5.5 on CursorBench 4.0 CursorBench 4.0 Effort: Max 55.5% cursor.com for Claude Sonnet 5.5 (max) on CursorBench 4.0 (opens in a new tab) CursorBench Accuracy Reported September 28, 2026 Benchmark leaderboard Cursor Independent Record for Claude Sonnet 5.5 on CursorBench 4.0 DeepSWE 1.1 Effort: Max 71.0% anthropic.com for Claude Sonnet 5.5 (max) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on DeepSWE 1.1 DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: Max Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 70.5% mercor.com for Claude Sonnet 5.5 (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@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation 58.1% vals.ai for Claude Sonnet 5.5 on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Finance Agent Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 5.5 on Finance Agent Benchmark 2 — October 2026 evaluation FrontierSWE 2 — October 2026 evaluation Configuration: Proximus harness, 5 trials, 20-hour budget 61.9% frontierswe.com for Claude Sonnet 5.5 on FrontierSWE 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) FrontierSWE Score Reported October 7, 2026 Benchmark leaderboard Proximal Independent Record for Claude Sonnet 5.5 on FrontierSWE 2 — October 2026 evaluation Global MMLU Original Effort: Max 92.1% anthropic.com for Claude Sonnet 5.5 (max) on Global MMLU Original (opens in a new tab) Average accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Global MMLU Original GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 95.6% epoch.ai for Claude Sonnet 5.5 (max) 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 Accuracy Reported October 7, 2026 Evaluated September 29, 2026 at 3:15 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 5.5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 95.2% mercor.com for Claude Sonnet 5.5 (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 Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot HLAB October 2026 evaluation 2.9% vals.ai for Claude Sonnet 5.5 on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) HLAB Task Pass Rate Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 5.5 on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Full set — No tools Effort: Low Configuration: No tools 41.4% anthropic.com for Claude Sonnet 5.5 (low) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — No tools Effort: Medium Configuration: No tools 43.2% anthropic.com for Claude Sonnet 5.5 (medium) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — No tools Effort: High Configuration: No tools 47.9% anthropic.com for Claude Sonnet 5.5 (high) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — No tools Effort: xHigh Configuration: No tools 53.0% anthropic.com for Claude Sonnet 5.5 (xhigh) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — No tools Effort: Max Configuration: No tools 56.9% anthropic.com for Claude Sonnet 5.5 (max) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — With tools Effort: Low Configuration: With tools 47.6% anthropic.com for Claude Sonnet 5.5 (low) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — With tools Humanity's Last Exam Full set — With tools Effort: Medium Configuration: With tools 50.5% anthropic.com for Claude Sonnet 5.5 (medium) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — With tools Humanity's Last Exam Full set — With tools Effort: High Configuration: With tools 56.7% anthropic.com for Claude Sonnet 5.5 (high) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — With tools Humanity's Last Exam Full set — With tools Effort: xHigh Configuration: With tools 62.0% anthropic.com for Claude Sonnet 5.5 (xhigh) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — With tools Humanity's Last Exam Full set — With tools Effort: Max Configuration: With tools 64.5% anthropic.com for Claude Sonnet 5.5 (max) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Humanity's Last Exam Full set — With tools MedXpertQA MM — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 80.7% mercor.com for Claude Sonnet 5.5 (max) on MedXpertQA MM — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 91.0% mercor.com for Claude Sonnet 5.5 (max) on MMLU-Pro Original — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on MMLU-Pro Original — Mercor single-shot MMMU-Pro 1,730 questions — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 85.8% mercor.com for Claude Sonnet 5.5 (max) on MMMU-Pro 1,730 questions — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on MMMU-Pro 1,730 questions — Mercor single-shot MILU Original Effort: Max 91.6% anthropic.com for Claude Sonnet 5.5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab) Average accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Multi-task Indic Language Understanding Benchmark Original SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 46.5% epoch.ai for Claude Sonnet 5.5 (max) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Evaluated September 29, 2026 at 3:15 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 5.5 on SimpleQA Verified Original — Epoch AI harness SpatialBench Verified Effort: Max 72.5% anthropic.com for Claude Sonnet 5.5 (max) on SpatialBench Verified (opens in a new tab) Task-pass accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on SpatialBench Verified SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: Max Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 50.3% mercor.com for Claude Sonnet 5.5 (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@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE-bench Multilingual Effort: Max 90.3% anthropic.com for Claude Sonnet 5.5 (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on SWE-bench Multilingual SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 90.9% mercor.com for Claude Sonnet 5.5 (max) on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 96.7% mercor.com for Claude Sonnet 5.5 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps SWE-bench Pro Public Effort: Max 81.3% anthropic.com for Claude Sonnet 5.5 (max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on SWE-bench Pro Public Terminal-Bench 2.1 — Vals AI Terminus 2 Configuration: Terminus-2 harness 83.1% vals.ai for Claude Sonnet 5.5 on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 5.5 on Terminal-Bench 2.1 — Vals AI Terminus 2 Terminal-Bench 4.0 Effort: Low 20.0% anthropic.com for Claude Sonnet 5.5 (low) on Terminal-Bench 4.0 (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Launch post Anthropic Self-reported Record for Claude Sonnet 5.5 on Terminal-Bench 4.0 Terminal-Bench 4.0 Effort: Medium 28.8% anthropic.com for Claude Sonnet 5.5 (medium) on Terminal-Bench 4.0 (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Launch post Anthropic Self-reported Record for Claude Sonnet 5.5 on Terminal-Bench 4.0 Terminal-Bench 4.0 Effort: High 43.0% anthropic.com for Claude Sonnet 5.5 (high) on Terminal-Bench 4.0 (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Launch post Anthropic Self-reported Record for Claude Sonnet 5.5 on Terminal-Bench 4.0 Terminal-Bench 4.0 Effort: xHigh 61.5% anthropic.com for Claude Sonnet 5.5 (xhigh) on Terminal-Bench 4.0 (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Launch post Anthropic Self-reported Record for Claude Sonnet 5.5 on Terminal-Bench 4.0 Terminal-Bench 4.0 Effort: Max 70.6% anthropic.com for Claude Sonnet 5.5 (max) on Terminal-Bench 4.0 (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Terminal-Bench 4.0 Terminal-Bench 4.0 — Claude Code Effort: Max Configuration: Claude Code harness 61.8% tbench.ai for Claude Sonnet 5.5 (max) on Terminal-Bench 4.0 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Benchmark leaderboard Terminal-Bench Independent Terminal-Bench Team Record for Claude Sonnet 5.5 on Terminal-Bench 4.0 — Claude Code Terminal-Bench 4.0 — Mercor mini-swe-agent Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 8 hours 51.5% mercor.com for Claude Sonnet 5.5 (max) on Terminal-Bench 4.0 — Mercor mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on Terminal-Bench 4.0 — Mercor mini-swe-agent Terminal-Bench Science 0.1 Effort: Max 59.9% anthropic.com for Claude Sonnet 5.5 (max) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Terminal-Bench Science 0.1 Toolathlon Verified Effort: Max 77.8% anthropic.com for Claude Sonnet 5.5 (max) on Toolathlon Verified (opens in a new tab) Tasks completed Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Toolathlon Verified Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Configuration: OpenHands harness 92.4% vals.ai for Claude Sonnet 5.5 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Vibe Code Bench Score Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 5.5 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation