List your company

Reasoning & General on HLE

51.8ScoreKimi K2.5
23.7231.0138.345.59Feb 17, 2026

Evaluation results

MethodLinks
Kimi K2.5Tool Use=w/ Tools2026.0251.8—
GLM-5Tool Use=w/ Tools2026.0250.4—
GLM-4.7Tool Use=w/ Tools2026.0242.8—
DeepSeek-V3.2Tool Use=w/ Tools2026.0240.8—
Gemini 3 ProTool Use=None2026.0237.2—
GPT-5.2 (xhigh)Tool Use=None2026.0235.4—
Kimi K2.5Tool Use=None2026.0231.5—
GLM-5Tool Use=None2026.0230.5—
Claude Opus 4.5Tool Use=None2026.0228.4—
DeepSeek-V3.2Tool Use=None2026.0225.1—
GLM-4.7Tool Use=None2026.0224.8—
Claude Opus 4.5Tool Use=w/ Tools, Evaluation Set=Full set2026.02—43.4
Gemini 3 ProTool Use=w/ Tools, Evaluation Set=Full set2026.02—45.8
GPT-5.2 (xhigh)Tool Use=w/ Tools, Evaluation Set=Full set2026.02—45.5