Skip to content
Agents tracked: 502 Releases (7d): 613 Agent status: 4 with issuesSince last limit reset: Claude 7d · Codex 5d For AI agents: Markdown Updated Nov 18, 2026

Claude Fable 5.2 is best at knowledge with 94.8, 6.3 ahead of Gemini 4 Carbon

Knowledge: average of 2 tests (GPQA Diamond, SimpleQA Verified), 0 to 100. Live chart from AgentGid, updated daily.

Claude Fable 5.2 is best at knowledge with 94.8, 6.3 ahead of Gemini 4 Carbon

Knowledge: average of 2 tests (GPQA Diamond, SimpleQA Verified), 0 to 100

0255075100Claude Fable 5.2 (Anthropic): 94.8Claude Fable 5.294.8Gemini 4 Carbon (Google): 88.5Gemini 4 Carbon88.5Gemini 4 Argon (Google): 87.6Gemini 4 Argon87.6GPT-6 Astra (OpenAI): 86.9GPT-6 Astra86.9GPT-6.1 Sol (OpenAI): 85.8GPT-6.1 Sol85.8Gemini 3.1 Pro Preview (Google): 85.0Gemini 3.1 Pro Preview85.0Gemini 3.8 Flash (Google): 83.7Gemini 3.8 Flash83.7Gemini 3.7 Flash (Google): 83.1Gemini 3.7 Flash83.1GPT-5.6 Sol (OpenAI): 82.4GPT-5.6 Sol82.4Claude Opus 5.5 (Anthropic): 81.6Claude Opus 5.581.6Gemini 3.6 Flash (Google): 81.1Gemini 3.6 Flash81.1Gemini 3.5 Flash (Google): 80.2Gemini 3.5 Flash80.2
Each model's best effort level. Models need 2 tests in this group to be listed; less than 1 point apart is a tie (=). Source: Gid Bench by AgentGid from Epoch AI (CC BY 4.0) and makers' launch pages · Nov 17, 2026.

Put this chart on your site

The chart updates by itself. Please keep the link to the source.

More charts