Epoch AI - Vending Bench 2 — leaderboard
Metric: Score. Source: epoch.ai. 54 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 9619.37 |
| 2 | GPT-5.5 | 7523.84 |
| 3 | GPT-5.6 Terra | 7343.21 |
| 4 | Kimi K2.6 | 6204.57 |
| 5 | GPT-5.4 | 6144.18 |
| 6 | GPT-5.3 Codex | 5940.12 |
| 7 | Claude Fable 5 (High) | 5680.26 |
| 8 | GLM-5.1 | 5634.41 |
| 9 | Gemini 3 Pro (Preview) | 5478.16 |
| 10 | Qwen 3.6 Plus | 5114.87 |
| 11 | Kimi K2.7 Code | 5082.94 |
| 12 | Claude Opus 4.5 (20251101) (Unknown) | 4967.06 |
| 13 | Claude Fable 5 (Max) | 4966.64 |
| 14 | Grok 4.20 | 4662.85 |
| 15 | Claude Fable 5 | 4529.94 |
Interactive version: theaggregate.ai/benchmark?slug=epoch-ai-vending-bench-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.