GPQA Diamond Reported as: extended thinking 87.0% assets.anthropic.com for Claude Opus 4.5 (extended thinking) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported November 24, 2025 System card Anthropic Self-reported Record for Claude Opus 4.5 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Configuration: Epoch AI harness 80.7% epoch.ai for Claude Opus 4.5 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 November 24, 2025 at 7:57 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Opus 4.5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 79.5% vals.ai for Claude Opus 4.5 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 4.5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness GPQA Diamond — Vals AI harness Reported as: thinking Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 85.9% vals.ai for Claude Opus 4.5 (thinking) 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 4.5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness Humanity's Last Exam Full set — No tools Reported as: extended thinking Configuration: No tools 30.8% assets.anthropic.com for Claude Opus 4.5 (extended thinking) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported November 24, 2025 System card Anthropic Self-reported Record for Claude Opus 4.5 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — Scale AI evaluation 14.2% labs.scale.com for Claude Opus 4.5 on Humanity's Last Exam Full set — Scale AI evaluation (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 3, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Opus 4.5 on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Full set — Scale AI evaluation Reported as: thinking 25.2% labs.scale.com for Claude Opus 4.5 (thinking) on Humanity's Last Exam Full set — Scale AI evaluation (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 3, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Opus 4.5 on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Text only — Scale AI evaluation 13.9% labs.scale.com for Claude Opus 4.5 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 Accuracy Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Opus 4.5 on Humanity's Last Exam Text only — Scale AI evaluation Humanity's Last Exam Text only — Scale AI evaluation Reported as: thinking 26.3% labs.scale.com for Claude Opus 4.5 (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 Accuracy Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Opus 4.5 on Humanity's Last Exam Text only — Scale AI evaluation MCP Atlas Public, April 2026 update Effort: High 69.8% labs.scale.com for Claude Opus 4.5 (high) 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 4.5 on MCP Atlas Public, April 2026 update MMLU-Pro Original — Vals AI harness Configuration: Vals AI harness 85.6% vals.ai for Claude Opus 4.5 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 4.5 on MMLU-Pro Original — Vals AI harness MMLU-Pro Original — Vals AI harness Reported as: thinking Configuration: Vals AI harness 87.3% vals.ai for Claude Opus 4.5 (thinking) 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 4.5 on MMLU-Pro Original — Vals AI harness MMMU-Pro Vals AI harness Configuration: Vals AI harness 81.1% vals.ai for Claude Opus 4.5 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 4.5 on MMMU-Pro Vals AI harness MMMU-Pro Vals AI harness Reported as: thinking Configuration: Vals AI harness 82.9% vals.ai for Claude Opus 4.5 (thinking) 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 4.5 on MMMU-Pro Vals AI harness OSWorld Verified Reported as: extended thinking 66.3% assets.anthropic.com for Claude Opus 4.5 (extended thinking) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported November 24, 2025 System card Anthropic Self-reported Record for Claude Opus 4.5 on OSWorld Verified Riemann-bench October 2026 leaderboard Effort: Max Reported as: Adaptive/Max 11.2% surgehq.ai for Claude Opus 4.5 (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 4.5 on Riemann-bench October 2026 leaderboard SWE-bench Multilingual — mini-swe-agent Configuration: mini-swe-agent harness 70.7% github.com for Claude Opus 4.5 on SWE-bench Multilingual — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 13, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Opus 4.5 on SWE-bench Multilingual — mini-swe-agent SWE-bench Verified Effort: None Reported as: no thinking 80.9% assets.anthropic.com for Claude Opus 4.5 (no thinking) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported November 24, 2025 System card Anthropic Self-reported Record for Claude Opus 4.5 on SWE-bench Verified SWE-bench Verified — Epoch AI harness Configuration: Epoch AI harness 76.7% epoch.ai for Claude Opus 4.5 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 5, 2026 at 10:06 PM UTC Benchmark leaderboard Epoch AI Independent Record for Claude Opus 4.5 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — mini-swe-agent Effort: Medium Configuration: mini-swe-agent harness 74.4% github.com for Claude Opus 4.5 (medium) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported November 24, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Opus 4.5 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — mini-swe-agent Effort: High Configuration: mini-swe-agent harness 76.8% github.com for Claude Opus 4.5 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Opus 4.5 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — Vals AI mini-swe-agent Reported as: thinking Configuration: mini-swe-agent harness 76.4% vals.ai for Claude Opus 4.5 (thinking) 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 4.5 on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Private — Scale AI SWE-Agent Configuration: SWE-Agent harness, 250 turns, uncapped cost 23.4% labs.scale.com for Claude Opus 4.5 on SWE-bench Pro Private — Scale AI SWE-Agent (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Opus 4.5 on SWE-bench Pro Private — Scale AI SWE-Agent SWE-bench Pro Public — Scale AI SWE-Agent Configuration: SWE-Agent harness, 250 turns, uncapped cost 45.9% labs.scale.com for Claude Opus 4.5 on SWE-bench Pro Public — Scale AI SWE-Agent (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Claude Opus 4.5 on SWE-bench Pro Public — Scale AI SWE-Agent Terminal-Bench 2.0 Reported as: extended thinking (128K) 59.8% assets.anthropic.com for Claude Opus 4.5 (extended thinking (128K)) on Terminal-Bench 2.0 (opens in a new tab) Terminal-Bench Accuracy Reported November 24, 2025 System card Anthropic Self-reported Record for Claude Opus 4.5 on Terminal-Bench 2.0 Terminal-Bench 2.0 — Vals AI Terminus 2 Configuration: Terminus-2 harness 58.4% vals.ai for Claude Opus 4.5 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 4.5 on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.0 — Vals AI Terminus 2 Reported as: thinking Configuration: Terminus-2 harness 53.9% vals.ai for Claude Opus 4.5 (thinking) 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 4.5 on Terminal-Bench 2.0 — Vals AI Terminus 2 Toolathlon Original 43.5% toolathlon.xyz for Claude Opus 4.5 on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported November 27, 2025 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for Claude Opus 4.5 on Toolathlon Original Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Reported as: thinking Configuration: OpenHands harness 20.6% vals.ai for Claude Opus 4.5 (thinking) 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 Opus 4.5 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation τ³-bench τ³ — Airline Effort: High 84.0% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Claude Opus 4.5 (high) on τ³-bench τ³ — Airline (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 5, 2026 Evaluated May 5, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for Claude Opus 4.5 on τ³-bench τ³ — Airline τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading Effort: High Configuration: AllTools retrieval 24.7% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Claude Opus 4.5 (high) on τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 5, 2026 Evaluated May 5, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for Claude Opus 4.5 on τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading τ³-bench τ³ — Retail Effort: High 79.6% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Claude Opus 4.5 (high) on τ³-bench τ³ — Retail (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 5, 2026 Evaluated May 5, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for Claude Opus 4.5 on τ³-bench τ³ — Retail τ³-bench τ³ — Telecom Effort: High 92.3% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for Claude Opus 4.5 (high) on τ³-bench τ³ — Telecom (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 5, 2026 Evaluated May 5, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for Claude Opus 4.5 on τ³-bench τ³ — Telecom