MERA - MathLogicQA: leaderboard
MERA is the Russian open benchmark run by the AI Alliance Russia; this is its MathLogicQA task: word problems that need a logical step before the arithmetic. Each MERA task keeps its own native metric, so the boards are not on one shared scale.
Metric: Accuracy (%). Source: mera.a-ai.ru. Saturation forecast: Estimated already saturated. 632 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 99.83 | #63 |
| 2 | GLM-5.1 | 99.74 | #97 |
| 3 | Qwen 3 235B A22B 2507 (Thinking) | 99.74 | #260 (Qwen 3 235B A22B 2507) |
| 4 | Qwen 3 30B A3B 2507 (Thinking) | 99.74 | #376 (Qwen 3 30B A3B 2507) |
| 5 | Qwen 3.6 27B | 99.65 | #170 |
| 6 | Kimi K2.5 | 99.56 | #144 |
| 7 | Qwen 3.5 27B | 99.48 | #187 |
| 8 | Qwen 3 4B | 99.39 | #829 |
| 9 | Qwen 3.5 122B A10B | 99.3 | #173 |
| 10 | MiniMax-M2.7 | 99.3 | #258 |
| 11 | Qwen 3 32B | 99.21 | #443 |
| 12 | Qwen 3.6 35B A3B | 99.21 | #226 |
| 13 | Qwen 3 4B 2507 (Thinking) | 99.13 | #538 (Qwen 3 4B 2507) |
| 14 | Qwen 3.5 9B | 99.04 | #379 |
| 15 | Qwen 3 Next 80B A3B (Thinking) | 99.04 | #320 (Qwen 3 Next 80B A3B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mera-mathlogicqa · How It Works · Data refreshed daily, snapshot 2026-10-20.