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

Same model, different agent: up to 8 points apart (Gemini 3 Pro)

Terminal-Bench 2.1: share of tasks solved by each agent on the same model; ringed = the lab's own agent. Live chart from AgentGid, updated daily.

Same model, different agent: up to 8 points apart (Gemini 3 Pro)

Terminal-Bench 2.1: share of tasks solved by each agent on the same model; ringed = the lab's own agent

60%70%80%90%Fable 5Terminus 2 + Fable 5: 80.5%Claude Code + Fable 5: 83.8%Claude Code 83.8%GPT-5.5Terminus 2 + GPT-5.5: 78.0%Codex + GPT-5.5: 83.2%Codex 83.2%Gemini 3 ProTerminus 2 + Gemini 3 Pro: 73.9%Gemini CLI + Gemini 3 Pro: 65.8%Terminus 2 73.9% · Gemini CLI 65.8%Opus 4.7Terminus 2 + Opus 4.7: 66.1%Claude Code + Opus 4.7: 68.9%Claude Code 68.9%Gemini 3.1 ProTerminus 2 + Gemini 3.1 Pro: 65.6%Gemini CLI + Gemini 3.1 Pro: 65.8%Gemini CLI 65.8%
Best run of each agent on each model. Scores are not comparable between Terminal-Bench versions. Source: Terminal-Bench (tbench.ai), as published · Sep 3, 2026.

Put this chart on your site

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

More charts