DataVista - Level 2 (subtitles): leaderboard
Metric: Exact-match accuracy (%). Source: arxiv.org. Saturation forecast: Around January 2027. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 71.5 | #55 |
| 2 | Gemini 3 Flash | 68.8 | #96 |
| 3 | GPT-5 | 66.7 | #94 |
| 4 | Claude Sonnet 4.6 | 60.7 | #89 |
| 5 | Qwen 3 VL 32B Instruct | 48.5 | #278 |
| 6 | Qwen 2.5 VL 32B Instruct | 47.8 | #440 |
| 7 | GPT-4o | 44.8 | #335 |
| 8 | InternVL3-8B | 38.2 | #610 |
| 9 | Qwen 3 VL 8B Instruct | 33.9 | #406 |
| 10 | Qwen 2.5 VL 7B Instruct | 33.9 | #650 |
| 11 | Qwen 3 VL 4B Instruct | 30.5 | #509 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=datavista-level-2-subtitles · How It Works · Data refreshed daily, snapshot 2026-10-13.