APEX-Agents Original Effort: High 43.0% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on APEX-Agents Original AutomationBench 1.0.6 Effort: Low 2.9% zapier.com for Claude Sonnet 4.6 (low) on AutomationBench 1.0.6 (opens in a new tab) Archived copy (opens in a new tab) Task pass rate Reported October 7, 2026 Benchmark leaderboard Zapier Independent Zapier AutomationBench Team Record for Claude Sonnet 4.6 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 3.7% zapier.com for Claude Sonnet 4.6 (medium) on AutomationBench 1.0.6 (opens in a new tab) Archived copy (opens in a new tab) Task pass rate Reported October 7, 2026 Benchmark leaderboard Zapier Independent Zapier AutomationBench Team Record for Claude Sonnet 4.6 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 5.0% zapier.com for Claude Sonnet 4.6 (high) on AutomationBench 1.0.6 (opens in a new tab) Archived copy (opens in a new tab) Task pass rate Reported October 7, 2026 Benchmark leaderboard Zapier Independent Zapier AutomationBench Team Record for Claude Sonnet 4.6 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Max 5.3% zapier.com for Claude Sonnet 4.6 (max) on AutomationBench 1.0.6 (opens in a new tab) Archived copy (opens in a new tab) Task pass rate Reported October 7, 2026 Benchmark leaderboard Zapier Independent Zapier AutomationBench Team Record for Claude Sonnet 4.6 on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: High Configuration: Mercor web research agent, 100 steps, 3 hours 56.7% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on BrowseComp 130-question subset — Mercor web research agent CharXiv Descriptive and reasoning — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 90.5% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on CharXiv Descriptive and reasoning — Mercor single-shot DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: High Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 34.2% mercor.com for Claude Sonnet 4.6 (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@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 4.6 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation 51.0% vals.ai for Claude Sonnet 4.6 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 4.6 on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond Effort: Max Reported as: adaptive thinking, max 89.9% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: Medium Configuration: Epoch AI harness 83.3% epoch.ai for Claude Sonnet 4.6 (medium) 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 July 13, 2026 at 5:28 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 4.6 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: High Configuration: Epoch AI harness 83.3% epoch.ai for Claude Sonnet 4.6 (high) 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 July 13, 2026 at 5:28 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 4.6 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 78.8% epoch.ai for Claude Sonnet 4.6 (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 August 6, 2026 at 10:21 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 4.6 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 84.7% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot GPQA Diamond — Vals AI harness Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 85.6% vals.ai for Claude Sonnet 4.6 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4.6 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation 5.0% vals.ai for Claude Sonnet 4.6 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 4.6 on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Full set — No tools Effort: Max Reported as: adaptive thinking, max Configuration: No tools 33.2% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — With tools Effort: Max Reported as: adaptive thinking, max Configuration: With tools 49.0% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on Humanity's Last Exam Full set — With tools Humanity's Last Exam Text only — Mercor single-shot Effort: Medium Configuration: Mercor single-shot agent 29.2% mercor.com for Claude Sonnet 4.6 (medium) 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 Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 4.6 on Humanity's Last Exam Text only — Mercor single-shot Humanity's Last Exam Text only — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 24.4% mercor.com for Claude Sonnet 4.6 (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 Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 4.6 on Humanity's Last Exam Text only — Mercor single-shot MCP Atlas Public, April 2026 update 69.5% labs.scale.com for Claude Sonnet 4.6 on MCP Atlas Public, April 2026 update (opens in a new tab) Pass rate Reported September 24, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Sonnet 4.6 on MCP Atlas Public, April 2026 update MedXpertQA MM — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 61.7% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 88.0% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Vals AI harness Configuration: Vals AI harness 87.3% vals.ai for Claude Sonnet 4.6 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4.6 on MMLU-Pro Original — Vals AI harness MMMU-Pro 1,730 questions — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 74.6% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro No tools Effort: Max Reported as: adaptive thinking, max Configuration: No tools 74.5% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Overall (Standard 10 options + Vision) Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on MMMU-Pro No tools MMMU-Pro Vals AI harness Configuration: Vals AI harness 83.6% vals.ai for Claude Sonnet 4.6 on MMMU-Pro Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Standard (4 options) Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4.6 on MMMU-Pro Vals AI harness OSWorld Verified Effort: Max Reported as: adaptive thinking, max 72.5% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on OSWorld Verified OSWorld Verified — 100 steps Configuration: 100-step limit 72.1% os-world.github.io for Claude Sonnet 4.6 on OSWorld Verified — 100 steps (opens in a new tab) Archived copy (opens in a new tab) OSWorld-Verified success rate Reported March 8, 2026 Benchmark leaderboard OSWorld Independent XLang Lab Record for Claude Sonnet 4.6 on OSWorld Verified — 100 steps SimpleQA Verified Original — Epoch AI harness Effort: High Configuration: Epoch AI harness 35.5% epoch.ai for Claude Sonnet 4.6 (high) 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 August 10, 2026 at 10:42 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 4.6 on SimpleQA Verified Original — Epoch AI harness SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 32.8% epoch.ai for Claude Sonnet 4.6 (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 August 27, 2026 at 7:27 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 4.6 on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: High Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 35.5% mercor.com for Claude Sonnet 4.6 (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@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 4.6 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE Atlas Codebase QnA — Public; Claude Code Configuration: Claude Code harness 31.2% labs.scale.com for Claude Sonnet 4.6 on SWE Atlas Codebase QnA — Public; Claude Code (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Sonnet 4.6 on SWE Atlas Codebase QnA — Public; Claude Code SWE Atlas Refactoring — Claude Code Configuration: Claude Code harness 32.2% labs.scale.com for Claude Sonnet 4.6 on SWE Atlas Refactoring — Claude Code (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Sonnet 4.6 on SWE Atlas Refactoring — Claude Code SWE-bench Multilingual Effort: Max Reported as: adaptive thinking, max 75.9% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on SWE-bench Multilingual SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: High Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 78.1% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified Effort: Max Reported as: adaptive thinking, max 79.6% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on SWE-bench Verified SWE-bench Verified — Epoch AI harness Configuration: Epoch AI harness 75.2% epoch.ai for Claude Sonnet 4.6 on SWE-bench Verified — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Evaluated February 21, 2026 at 10:32 AM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Sonnet 4.6 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Effort: High Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 79.1% mercor.com for Claude Sonnet 4.6 (high) 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 4.6 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Vals AI mini-swe-agent Configuration: mini-swe-agent harness 77.4% vals.ai for Claude Sonnet 4.6 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4.6 on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.0 Effort: Max Reported as: no thinking, max effort 59.1% www-cdn.anthropic.com for Claude Sonnet 4.6 (no thinking, max effort) on Terminal-Bench 2.0 (opens in a new tab) Terminal-Bench Accuracy Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on Terminal-Bench 2.0 Terminal-Bench 2.0 — Vals AI Terminus 2 Configuration: Terminus-2 harness 59.6% vals.ai for Claude Sonnet 4.6 on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported June 4, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4.6 on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.1 — Vals AI Terminus 2 Configuration: Terminus-2 harness 57.3% vals.ai for Claude Sonnet 4.6 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 4.6 on Terminal-Bench 2.1 — Vals AI Terminus 2 Toolathlon Original 44.8% toolathlon.xyz for Claude Sonnet 4.6 on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported February 23, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for Claude Sonnet 4.6 on Toolathlon Original Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation Configuration: Claude Code harness 55.8% vals.ai for Claude Sonnet 4.6 on Vibe Code Bench 1.1 — Claude Code, 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 4.6 on Vibe Code Bench 1.1 — Claude Code, October 2026 evaluation Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Configuration: OpenHands harness 51.5% vals.ai for Claude Sonnet 4.6 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 4.6 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation