Agentic on Vending-Bench 2
5,478ScoreGemini 3 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 3 Pro2026.02 | 5,478 | |
| Claude Opus 4.52026.02 | 4,967 | |
| GLM-52026.02 | 4,432 | |
| GPT-5.2 (xhigh)2026.02 | 3,591 | |
| GLM-4.72026.02 | 2,377 | |
| Kimi K2.52026.02 | 1,198 | |
| DeepSeek-V3.22026.02 | 1,034 |