APEX-Agents Original Effort: Max 48.9% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on APEX-Agents Original AutomationBench 1.0.6 Effort: Low 13.6% zapier.com for Claude Opus 4.8 (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 Opus 4.8 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 14.0% zapier.com for Claude Opus 4.8 (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 Opus 4.8 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 16.1% zapier.com for Claude Opus 4.8 (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 Opus 4.8 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: xHigh 16.9% zapier.com for Claude Opus 4.8 (xhigh) 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 Opus 4.8 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Max 16.4% zapier.com for Claude Opus 4.8 (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 Opus 4.8 on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: Max Configuration: Mercor web research agent, 100 steps, 3 hours 73.7% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on BrowseComp 130-question subset — Mercor web research agent Chartography October 2026 leaderboard Effort: Max Reported as: Adaptive/Max 15.9% surgehq.ai for Claude Opus 4.8 (Adaptive/Max) on Chartography October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Chartography Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for Claude Opus 4.8 on Chartography October 2026 leaderboard CharXiv Descriptive and reasoning — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 93.2% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on CharXiv Descriptive and reasoning — Mercor single-shot DeepSWE 1.1 Effort: Max 59.0% deepswe.datacurve.ai for Claude Opus 4.8 (max) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Benchmark leaderboard Datacurve Independent Record for Claude Opus 4.8 on DeepSWE 1.1 DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: Max Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 59.6% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation 53.9% vals.ai for Claude Opus 4.8 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 Opus 4.8 on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond Effort: Max Reported as: adaptive thinking, max 93.6% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: None Configuration: Epoch AI harness 85.4% epoch.ai for Claude Opus 4.8 (none) 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 10:19 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Opus 4.8 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Low Configuration: Epoch AI harness 88.4% epoch.ai for Claude Opus 4.8 (low) 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 10:19 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Opus 4.8 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 91.0% epoch.ai for Claude Opus 4.8 (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 June 7, 2026 at 11:03 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Opus 4.8 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 92.0% mercor.com for Claude Opus 4.8 (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 Opus 4.8 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 92.4% vals.ai for Claude Opus 4.8 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 Opus 4.8 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation 9.6% vals.ai for Claude Opus 4.8 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 Opus 4.8 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 49.8% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 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 57.9% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on Humanity's Last Exam Full set — With tools Humanity's Last Exam Text only — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 44.8% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on Humanity's Last Exam Text only — Mercor single-shot Humanity's Last Exam Text only — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 37.1% mercor.com for Claude Opus 4.8 (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 Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.8 on Humanity's Last Exam Text only — Mercor single-shot MCP Atlas Public, April 2026 update Effort: Max 82.2% labs.scale.com for Claude Opus 4.8 (max) 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 Opus 4.8 on MCP Atlas Public, April 2026 update MedXpertQA MM — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 72.5% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 90.0% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Vals AI harness Configuration: Vals AI harness 89.6% vals.ai for Claude Opus 4.8 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 Opus 4.8 on MMLU-Pro Original — Vals AI harness MMMU-Pro 1,730 questions — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 79.5% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro Vals AI harness Configuration: Vals AI harness 86.6% vals.ai for Claude Opus 4.8 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 Opus 4.8 on MMMU-Pro Vals AI harness OSWorld Verified Effort: Max Reported as: adaptive thinking, max 83.4% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on OSWorld Verified PostTrainBench 1.1 — Claude Code Effort: High Configuration: Claude Code harness 33.8% posttrainbench.com for Claude Opus 4.8 (High) on PostTrainBench 1.1 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) PostTrainBench Weighted Aggregate Reported October 6, 2026 Benchmark leaderboard PostTrainBench Independent PostTrainBench Team Record for Claude Opus 4.8 on PostTrainBench 1.1 — Claude Code PostTrainBench 1.1 — Claude Code Effort: Max Configuration: Claude Code harness 32.9% posttrainbench.com for Claude Opus 4.8 (Max) on PostTrainBench 1.1 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) PostTrainBench Weighted Aggregate Reported October 6, 2026 Benchmark leaderboard PostTrainBench Independent PostTrainBench Team Record for Claude Opus 4.8 on PostTrainBench 1.1 — Claude Code PostTrainBench 1.2 — Claude Code Effort: High Configuration: Claude Code harness 30.7% posttrainbench.com for Claude Opus 4.8 (High) on PostTrainBench 1.2 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) PostTrainBench Weighted Aggregate Reported October 6, 2026 Benchmark leaderboard PostTrainBench Independent PostTrainBench Team Record for Claude Opus 4.8 on PostTrainBench 1.2 — Claude Code PostTrainBench 1.2 — Claude Code Effort: Max Configuration: Claude Code harness 31.0% posttrainbench.com for Claude Opus 4.8 (Max) on PostTrainBench 1.2 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) PostTrainBench Weighted Aggregate Reported October 6, 2026 Benchmark leaderboard PostTrainBench Independent PostTrainBench Team Record for Claude Opus 4.8 on PostTrainBench 1.2 — Claude Code Riemann-bench October 2026 leaderboard Effort: Max Reported as: Adaptive/Max 47.2% surgehq.ai for Claude Opus 4.8 (Adaptive/Max) on Riemann-bench October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Riemann-bench Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for Claude Opus 4.8 on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 53.0% epoch.ai for Claude Opus 4.8 (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 Opus 4.8 on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: Max Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 44.4% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE Atlas Codebase QnA — Public; Claude Code Effort: xHigh Configuration: Claude Code harness 57.3% labs.scale.com for Claude Opus 4.8 (xhigh) 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 Opus 4.8 on SWE Atlas Codebase QnA — Public; Claude Code SWE Atlas Refactoring — Claude Code Configuration: Claude Code harness 46.7% labs.scale.com for Claude Opus 4.8 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 Opus 4.8 on SWE Atlas Refactoring — Claude Code SWE-bench Multilingual Effort: Max Reported as: adaptive thinking, max 84.4% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on SWE-bench Multilingual SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 86.6% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified Effort: Max Reported as: adaptive thinking, max 88.6% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on SWE-bench Verified SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 88.5% mercor.com for Claude Opus 4.8 (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 Opus 4.8 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Vals AI mini-swe-agent Configuration: mini-swe-agent harness 88.6% vals.ai for Claude Opus 4.8 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 Opus 4.8 on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Public Effort: Max Reported as: adaptive thinking, max 69.2% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on SWE-bench Pro Public Terminal-Bench 2.0 — Vals AI Terminus 2 Configuration: Terminus-2 harness 70.0% vals.ai for Claude Opus 4.8 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 Opus 4.8 on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.1 Effort: Max Reported as: adaptive thinking, max 74.6% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on Terminal-Bench 2.1 (opens in a new tab) Terminal-Bench Accuracy Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on Terminal-Bench 2.1 Terminal-Bench 2.1 — Vals AI Terminus 2 Configuration: Terminus-2 harness 71.9% vals.ai for Claude Opus 4.8 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 Opus 4.8 on Terminal-Bench 2.1 — Vals AI Terminus 2 Terminal-Bench 4.0 — Claude Code Effort: Max Configuration: Claude Code harness 23.6% tbench.ai for Claude Opus 4.8 (max) on Terminal-Bench 4.0 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported May 28, 2026 Benchmark leaderboard Terminal-Bench Independent Terminal-Bench Team Record for Claude Opus 4.8 on Terminal-Bench 4.0 — Claude Code Terminal-Bench 4.0 — Vals AI mini-swe-agent Configuration: mini-swe-agent harness 23.2% vals.ai for Claude Opus 4.8 on Terminal-Bench 4.0 — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Opus 4.8 on Terminal-Bench 4.0 — Vals AI mini-swe-agent