Finance Agent Benchmark 2 — October 2026 evaluation Effort: High 38.2% vals.ai for GPT-5.4 nano (high) 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 GPT-5.4 nano on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond — Epoch AI harness Effort: None Configuration: Epoch AI harness 55.6% epoch.ai for GPT-5.4 nano (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 7, 2026 at 12:01 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 nano on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Low Configuration: Epoch AI harness 72.2% epoch.ai for GPT-5.4 nano (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 7, 2026 at 12:00 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 nano on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: High Configuration: Epoch AI harness 78.5% epoch.ai for GPT-5.4 nano (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 April 14, 2026 at 3:07 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 nano 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 77.5% vals.ai for GPT-5.4 nano (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-5.4 nano on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Effort: High 0.0% vals.ai for GPT-5.4 nano (high) 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 GPT-5.4 nano on Harvey's Legal Agent Benchmark October 2026 evaluation MMLU-Pro Original — Vals AI harness Effort: High Configuration: Vals AI harness 77.2% vals.ai for GPT-5.4 nano (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-5.4 nano on MMLU-Pro Original — Vals AI harness MMMU-Pro Vals AI harness Effort: High Configuration: Vals AI harness 73.6% vals.ai for GPT-5.4 nano (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-5.4 nano on MMMU-Pro Vals AI harness SimpleQA Verified Original — Epoch AI harness Effort: High Configuration: Epoch AI harness 11.7% epoch.ai for GPT-5.4 nano (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-5.4 nano on SimpleQA Verified Original — Epoch AI harness SWE-bench Verified — Vals AI mini-swe-agent Effort: High Configuration: mini-swe-agent harness 69.8% vals.ai for GPT-5.4 nano (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-5.4 nano on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.0 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 39.9% vals.ai for GPT-5.4 nano (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-5.4 nano on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 41.6% vals.ai for GPT-5.4 nano (high) 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 GPT-5.4 nano on Terminal-Bench 2.1 — Vals AI Terminus 2 Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: High Configuration: OpenHands harness 26.1% vals.ai for GPT-5.4 nano (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-5.4 nano on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation