BabelArena - VitaBench: leaderboard
Metric: Pass^1 (%; VitaBench (food delivery, in-store consumption and online travel tasks; GPT-5.6-Sol judge); Pass^1: average single-trial task success over three trials, pooled over the 23 languages of BabelArena (7 high-, 8 medium- and 8 low-resource) including English; medium reasoning effort, temperature 0, Gemini-3.5-Flash as the simulated user). Source: arxiv.org. Saturation forecast: Around March 2028. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 (Medium) | 36.9 |
| 2 | Gemini 3.1 Pro (Preview) (Medium) | 34.3 |
| 3 | GPT-5.6 Terra (Medium) | 29.6 |
Interactive version: theaggregate.ai/benchmark?slug=babelarena-vitabench · How It Works · Data refreshed daily, snapshot 2026-09-26.