Scientific QA on Open question
0.85BertScoreSciReasoner
Evaluation Results
| Method | Links | |
|---|---|---|
| SciReasoner2026.07 | 0.85 | |
| GPT-5.52026.07 | 0.82 | |
| Kimi-K2.62026.07 | 0.82 | |
| DeepSeek-V4-Pro2026.07 | 0.82 | |
| Opus-4.72026.07 | 0.77 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| SciReasoner2026.07 | 0.85 | |
| GPT-5.52026.07 | 0.82 | |
| Kimi-K2.62026.07 | 0.82 | |
| DeepSeek-V4-Pro2026.07 | 0.82 | |
| Opus-4.72026.07 | 0.77 |