Scientific Reasoning on GPQA Diamond (Avg@16)
94.3Avg@16Gemini 3.1-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3.1-Pro2026.06 | 94.3 | |
| Claude Opus-4.72026.06 | 94.2 | |
| OpenAI GPT-5.42026.06 | 92.8 | |
| Claude Opus-4.62026.06 | 91.3 | |
| Kimi-K2.62026.06 | 91.1 | |
| DS-V4-Pro2026.06 | 90.1 | |
| GLM-5.12026.06 | 86.2 | |
| Ring-2.6-1Tvariant=xhigh2026.06 | 85.89 | |
| Ring-2.6-1Tvariant=high2026.06 | 76.1 |