GPQA Diamond — Epoch AI harness Effort: Medium Configuration: Epoch AI harness 85.4% epoch.ai for GPT-5 (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 August 7, 2025 at 7:34 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: High Configuration: Epoch AI harness 86.2% epoch.ai for GPT-5 (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 October 29, 2025 at 10:29 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Effort: High Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 85.6% vals.ai for GPT-5 (high) 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 GPT-5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness Humanity's Last Exam Full set — Scale AI evaluation 25.3% labs.scale.com for GPT-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 GPT-5 on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Text only — Scale AI evaluation 26.3% labs.scale.com for GPT-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 GPT-5 on Humanity's Last Exam Text only — Scale AI evaluation MMLU-Pro Original — Vals AI harness Effort: High Configuration: Vals AI harness 86.5% vals.ai for GPT-5 (high) 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 GPT-5 on MMLU-Pro Original — Vals AI harness MMMU-Pro Vals AI harness Effort: High Configuration: Vals AI harness 81.5% vals.ai for GPT-5 (high) 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 GPT-5 on MMMU-Pro Vals AI harness SimpleQA Verified Original — Epoch AI harness Effort: High Configuration: Epoch AI harness 50.1% epoch.ai for GPT-5 (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 27, 2026 at 7:28 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5 on SimpleQA Verified Original — Epoch AI harness SWE-bench Verified — Epoch AI harness Effort: Medium Configuration: Epoch AI harness 71.5% epoch.ai for GPT-5 (medium) 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 1:39 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — Epoch AI harness Effort: High Configuration: Epoch AI harness 73.6% epoch.ai for GPT-5 (high) 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 6, 2026 at 2:23 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — mini-swe-agent Effort: Medium Configuration: mini-swe-agent harness 65.0% github.com for GPT-5 (medium) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported August 7, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — Vals AI mini-swe-agent Effort: High Configuration: mini-swe-agent harness 69.0% vals.ai for GPT-5 (high) 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 GPT-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 14.9% labs.scale.com for GPT-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 GPT-5 on SWE-bench Pro Private — Scale AI SWE-Agent SWE-bench Pro Public — Scale AI SWE-Agent Effort: High Configuration: SWE-Agent harness, 250 turns, uncapped cost 41.8% labs.scale.com for GPT-5 (High) 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 GPT-5 on SWE-bench Pro Public — Scale AI SWE-Agent Terminal-Bench 2.0 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 37.1% vals.ai for GPT-5 (high) 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 GPT-5 on Terminal-Bench 2.0 — Vals AI Terminus 2 Toolathlon Original Effort: High 37.7% toolathlon.xyz for GPT-5 (high) on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported December 17, 2025 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for GPT-5 on Toolathlon Original Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: High Configuration: OpenHands harness 20.1% vals.ai for GPT-5 (high) 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 GPT-5 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation