VitaBench 2.0 — leaderboard

Metric: Avg@4 Full Context (self-reported). Source: benchmarklist.com. 20 models tracked.

Top models

#ModelScore
1Claude Opus 4.650.3
2Seed 2.0 Pro47.4
3DeepSeek V4 Pro47.2
4GPT-544.1
5GLM-5.142
6Claude Sonnet 4.541.7
7O340.3
8DeepSeek R1 052839.6
9GLM-4.536.4
10GLM-4.635.9
11MiniMax-M2.734.5
12Gemini 2.5 Pro33.1
13LongCat-Flash-Chat29.8
14Gemini 2.5 Flash28.2
15O4 Mini21

Interactive version: theaggregate.ai/benchmark?slug=vitabench-2-0 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.