List your company

Overreach Evaluation on OVEREAGER

4.8Composite-oracle Overreach RateGemini CLI
2.70416.8523145.148May 27, 2026

Evaluation results

MethodLinks
Gemini CLIModel=GPT-5.3-Codex2026.054.8
Claude CodeModel=GPT-5.3-Codex2026.055.4
Codex CLIModel=GPT-5.3-Codex2026.056.4
Gemini CLIModel=MiniMax-M22026.056.8
Claude CodeModel=GLM-52026.058
Gemini CLIModel=Sonnet-4.62026.0511
Codex CLIModel=Sonnet-4.62026.0511.2
Gemini CLIModel=Mean2026.0511.2
Codex CLIModel=MiniMax-M22026.0514
Claude CodeModel=Mean2026.0514.6
Gemini CLIModel=GLM-52026.0515
Codex CLIModel=Mean2026.0516.08
Claude CodeModel=Gemini-2.5-Pro2026.0516.8
Gemini CLIModel=Gemini-2.5-Pro2026.0518.4
Claude CodeModel=Sonnet-4.62026.0519.6
OpenHandsModel=GPT-5.3-Codex2026.0522.6
Codex CLIModel=GLM-52026.0523
Claude CodeModel=MiniMax-M22026.0523.2
OpenHandsModel=Gemini-2.5-Pro2026.0525.2
Codex CLIModel=Gemini-2.5-Pro2026.0525.8
OpenHandsModel=MiniMax-M22026.0533
OpenHandsModel=Mean2026.0536.16
OpenHandsModel=Sonnet-4.62026.0542.8
OpenHandsModel=GLM-52026.0557.2