MERA Multi - Image: leaderboard
MERA Multi image result: a submission's score over MERA's Russian image-understanding tasks, reduced by coverage when it skipped some of them. InternVL3 and InternVL3.5 image runs score near zero in MERA's data while their video runs do not. MERA's 0-1 result scaled to 0-100; higher is better. From the MERA Multi leaderboard (AI Alliance Russia); only submissions MERA shows publicly for the modality are included.
Metric: Score (%). Source: mera.a-ai.ru. Saturation forecast: Around February 2027. 60 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 27B | 65 | #182 |
| 2 | Qwen 3.5 27B | 64.8 | #192 |
| 3 | Qwen 3.5 122B A10B | 64.8 | #184 |
| 4 | Qwen 3.5 35B A3B | 63.6 | #268 |
| 5 | Qwen 3.6 35B A3B | 63.1 | #238 |
| 6 | Gemma 4 31B (IT) | 62 | #178 |
| 7 | Gemma 4 26B A4B (IT) | 57.1 | #293 |
| 8 | Qwen3 Omni 30B A3B Instruct | 55.4 | #401 |
| 9 | GPT-4.1 | 47.8 | #258 |
| 10 | gemma-4-E4B-it | 47.4 | #577 |
| 11 | Qwen 2.5 VL 72B Instruct | 40.6 | #383 |
| 12 | Gemma 4 E2B (IT) | 37 | #779 |
| 13 | Qwen 2 VL 72B Instruct | 33.3 | #551 |
| 14 | Qwen 2.5 VL 32B Instruct | 31.5 | #463 |
| 15 | Qwen 2.5 VL 7B Instruct | 25.6 | #650 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mera-multi-image · How It Works · Data refreshed daily, snapshot 2026-11-05.