Chemistry Reasoning on SUPERChem text only
63.2Avg@8Gemini-3-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-3-Pro2026.03 | 63.2 | |
| GPT-5.2-high2026.03 | 58 | |
| Gemini-3-Flash HighConfig=text-only2026.06 | 54.4 | |
| Seed-2.0-Pro2026.03 | 53 | |
| MiroThinker-H12026.03 | 51.3 | |
| Qwen3.5-397BEvaluation Setting=Internal evaluation2026.03 | 49.6 | |
| Seed2.0 LiteConfig=text-only2026.06 | 48 | |
| Claude-4.5-Opus2026.03 | 43.2 | |
| MiroThinker-1.72026.03 | 42.1 | |
| MiroThinker-1.7-mini2026.03 | 36.8 | |
| GPT-5-mini HighConfig=text-only2026.06 | 34.8 |