MERA v2 - GorillaHard: leaderboard
MERA v2 is the second generation of the Russian MERA suite, rebuilt after the v1 tasks saturated; this board is the hard split of API and function-calling selection.
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 | 76.2 | #26 |
| 2 | Claude Opus 5 | 68.3 | #12 |
| 3 | Gemini 3.7 Flash | 68.2 | #23 |
| 4 | GPT-5.6 Sol | 63.8 | #19 |
| 5 | GPT-5.6 Terra | 59.3 | #41 |
| 6 | MiniMax-M3 | 53.1 | #136 |
| 7 | Qwen 3.5 27B | 51.2 | #187 |
| 8 | GPT-5.6 Luna | 50.6 | #68 |
| 9 | Qwen 3.7 Flash | 50.6 | #171 |
| 10 | Qwen 3.6 27B | 47.5 | #170 |
| 11 | Grok 4.3 | 45.3 | #188 |
| 12 | Qwen 3.6 35B A3B | 44.7 | #226 |
| 13 | Qwen 3.5 397B A17B | 41.6 | #146 |
| 14 | Solar Pro 4 | 40.3 | #215 |
| 15 | MiMo-V2.5-Pro | 39.5 | #158 |
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-gorillahard · How It Works · Data refreshed daily, snapshot 2026-10-20.