Agentic on GDPval-AA Elo
1,462Elo ScoreGPT-5.2 (xhigh)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.2 (xhigh)2026.02 | 1,462 | |
| GLM-52026.02 | 1,409 | |
| Claude Opus 4.52026.02 | 1,400 | |
| Kimi K2.52026.02 | 1,288 | |
| Gemini 3 Pro2026.02 | 1,201 | |
| GLM-4.72026.02 | 1,198 | |
| DeepSeek-V3.22026.02 | 1,195 |