VitaBench 2.0 — leaderboard
Metric: Avg@4 Full Context (self-reported). Source: benchmarklist.com. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 50.3 |
| 2 | Seed 2.0 Pro | 47.4 |
| 3 | DeepSeek V4 Pro | 47.2 |
| 4 | GPT-5 | 44.1 |
| 5 | GLM-5.1 | 42 |
| 6 | Claude Sonnet 4.5 | 41.7 |
| 7 | O3 | 40.3 |
| 8 | DeepSeek R1 0528 | 39.6 |
| 9 | GLM-4.5 | 36.4 |
| 10 | GLM-4.6 | 35.9 |
| 11 | MiniMax-M2.7 | 34.5 |
| 12 | Gemini 2.5 Pro | 33.1 |
| 13 | LongCat-Flash-Chat | 29.8 |
| 14 | Gemini 2.5 Flash | 28.2 |
| 15 | O4 Mini | 21 |
Interactive version: theaggregate.ai/benchmark?slug=vitabench-2-0 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.