List your company

Scientific Reasoning on GPQA Diamond (Avg@16)

94.3Avg@16Gemini 3.1-Pro
75.37280.28685.290.114Jun 13, 2026

Evaluation results

MethodLinks
Gemini 3.1-Pro2026.0694.3
Claude Opus-4.72026.0694.2
OpenAI GPT-5.42026.0692.8
Claude Opus-4.62026.0691.3
Kimi-K2.62026.0691.1
DS-V4-Pro2026.0690.1
GLM-5.12026.0686.2
Ring-2.6-1Tvariant=xhigh2026.0685.89
Ring-2.6-1Tvariant=high2026.0676.1