Anthropic Claude Haiku 5.5 (max)20.6% anthropic.com for Claude Haiku 5.5 (max) on Terminal-Bench Science 0.1 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 7, 2026 System card Anthropic Self-reported Record for Claude Haiku 5.5 on Terminal-Bench Science 0.1 20018 OpenAI GPT-6.1 Sol (low)43.7% openai.com for GPT-6.1 Sol (low) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 10015 OpenAI GPT-6.1 Sol (high)51.1% openai.com for GPT-6.1 Sol (high) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 10015 OpenAI GPT-6.1 Sol (medium)47.6% openai.com for GPT-6.1 Sol (medium) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 10015 OpenAI GPT-6.1 Sol (xhigh)53.7% openai.com for GPT-6.1 Sol (xhigh) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 10015 OpenAI GPT-6.1 Sol (max)57.0% openai.com for GPT-6.1 Sol (max) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 10015 Anthropic Claude Sonnet 5.5 (max)59.9% anthropic.com for Claude Sonnet 5.5 (max) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on Terminal-Bench Science 0.1 20016 Anthropic Claude Opus 5.5 (adaptive thinking, max)58.7% anthropic.com for Claude Opus 5.5 (adaptive thinking, max) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 22, 2026 Launch post Anthropic Self-reported Record for Claude Opus 5.5 on Terminal-Bench Science 0.1 20015 OpenAI GPT-6 Astra 64.6% openai.com for GPT-6 Astra on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 3, 2026 Launch post OpenAI Self-reported Record for GPT-6 Astra on Terminal-Bench Science 0.1 10005 Anthropic Claude Fable 5.1 (xhigh)49.5% anthropic.com for Claude Fable 5.1 (xhigh) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 1, 2026 Launch post Anthropic Self-reported Record for Claude Fable 5.1 on Terminal-Bench Science 0.1 20004 Anthropic Claude Fable 5.1 (medium)35.7% anthropic.com for Claude Fable 5.1 (medium) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 1, 2026 Launch post Anthropic Self-reported Record for Claude Fable 5.1 on Terminal-Bench Science 0.1 20004 Anthropic Claude Fable 5.1 (low)26.3% anthropic.com for Claude Fable 5.1 (low) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 1, 2026 Launch post Anthropic Self-reported Record for Claude Fable 5.1 on Terminal-Bench Science 0.1 20004 Anthropic Claude Fable 5.1 (high)40.0% anthropic.com for Claude Fable 5.1 (high) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 1, 2026 Launch post Anthropic Self-reported Record for Claude Fable 5.1 on Terminal-Bench Science 0.1 20004 Anthropic Claude Fable 5.1 52.6% anthropic.com for Claude Fable 5.1 on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 1, 2026 Launch post Anthropic Self-reported Record for Claude Fable 5.1 on Terminal-Bench Science 0.1 20004