MERA Reason - Luzitania: leaderboard
MERA Reason is the Russian reasoning suite MERA launched on 2026-07-24, run as its own Hugging Face Space; this board is the Luzitania reasoning set.
Metric: Score. Source: huggingface.co. Saturation forecast: Around June 2027. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 58.96 | #37 |
| 2 | Gemma 4 31B (IT) | 43.43 | #176 |
| 3 | Qwen 3.5 122B A10B | 35.06 | #173 |
| 4 | Qwen 3.5 27B | 31.47 | #187 |
| 5 | GLM-5 | 29.48 | #141 |
| 6 | Gemma 4 26B A4B (IT) | 28.29 | #297 |
| 7 | Qwen 3.5 35B A3B | 27.89 | #256 |
| 8 | Qwen 3.6 27B | 25.1 | #170 |
| 9 | DeepSeek V4 Pro | 23.11 | #102 |
| 10 | DeepSeek V4 Flash | 22.71 | #137 |
| 11 | Qwen 3.6 35B A3B | 18.73 | #226 |
| 12 | Qwen 3 Next 80B A3B (Thinking) | 18.33 | #320 (Qwen 3 Next 80B A3B) |
| 13 | Qwen 3 30B A3B 2507 (Thinking) | 18.33 | #376 (Qwen 3 30B A3B 2507) |
| 14 | Qwen 3 4B 2507 (Thinking) | 16.73 | #538 (Qwen 3 4B 2507) |
| 15 | Qwen 3.5 9B | 13.94 | #379 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mera-reason-luzitania · How It Works · Data refreshed daily, snapshot 2026-10-20.