MERA v2 - Enantiosemy: leaderboard
MERA v2 is the second generation of the Russian MERA suite, rebuilt after the v1 tasks saturated; this board is enantiosemy, the Russian words that carry two opposite senses, disambiguated from context.
Metric: Score (%). Source: mera.a-ai.ru. Saturation forecast: Around January 2027. 40 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4.6 | 70.8 | #26 |
| 2 | GPT-5.6 Sol | 70.4 | #19 |
| 3 | Claude Opus 5 | 69 | #12 |
| 4 | Gemini 3.7 Flash | 62.6 | #23 |
| 5 | Grok 4.3 | 57.9 | #188 |
| 6 | GPT-5.6 Terra | 57.5 | #41 |
| 7 | GPT-5.6 Luna | 56.5 | #68 |
| 8 | Gemma 4 31B (IT) (Non-reasoning) | 55.8 | #176 (Gemma 4 31B (IT)) |
| 9 | Llama 4 Maverick Instruct | 49.6 | #456 |
| 10 | MiMo-V2.5-Pro | 49.4 | #158 |
| 11 | Qwen 3.5 397B A17B | 47.2 | #146 |
| 12 | Qwen 3.6 27B | 45 | #170 |
| 13 | Qwen 3.5 122B A10B | 43.8 | #173 |
| 14 | Qwen 3.5 27B | 43.3 | #187 |
| 15 | GigaChat 3.5 Reasoning | 42.3 | #167 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mera-v2-enantiosemy · How It Works · Data refreshed daily, snapshot 2026-10-20.