MERA - SimpleAr: leaderboard
MERA is the Russian open benchmark run by the AI Alliance Russia; this is its SimpleAr task: simple arithmetic, present as a floor check on the suite. Each MERA task keeps its own native metric, so the boards are not on one shared scale.
Metric: EM (%). Source: mera.a-ai.ru. Saturation forecast: Estimated already saturated. 631 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 100 | #110 |
| 2 | Claude Opus 4.6 | 100 | #63 |
| 3 | Gemini 2.0 Flash | 100 | #342 |
| 4 | Gemma 4 31B (IT) | 100 | #176 |
| 5 | DeepSeek V3 | 100 | #321 |
| 6 | Qwen 3.5 27B | 100 | #187 |
| 7 | Claude 3.7 Sonnet | 100 | #249 |
| 8 | Qwen 3.5 122B A10B | 100 | #173 |
| 9 | Claude Opus 4.5 | 100 | #83 |
| 10 | Gemma 4 26B A4B (IT) | 100 | #297 |
| 11 | Qwen 3 235B A22B 2507 (Thinking) | 100 | #260 (Qwen 3 235B A22B 2507) |
| 12 | Qwen 3 30B A3B 2507 (Thinking) | 100 | #376 (Qwen 3 30B A3B 2507) |
| 13 | Qwen 3 4B 2507 (Thinking) | 100 | #538 (Qwen 3 4B 2507) |
| 14 | Qwen 2.5 Max | 100 | #416 |
| 15 | Median Human | 100 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mera-simplear · How It Works · Data refreshed daily, snapshot 2026-10-20.