MERA - LCS: leaderboard
MERA is the Russian open benchmark run by the AI Alliance Russia; this is its LCS task: longest common subsequence over two strings, an algorithmic probe scored by exact match. 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 | GPT-5.4 | 97.4 | #79 |
| 2 | Claude Opus 4.6 | 96.4 | #63 |
| 3 | MiniMax-M2.7 | 85.6 | #258 |
| 4 | GLM-5.1 | 61.6 | #97 |
| 5 | Qwen 3.6 27B | 57.2 | #170 |
| 6 | Qwen 3 32B | 56.8 | #443 |
| 7 | Qwen 3 30B A3B 2507 (Thinking) | 55.6 | #376 (Qwen 3 30B A3B 2507) |
| 8 | Qwen 3.6 35B A3B | 54.6 | #226 |
| 9 | Qwen 3 235B A22B 2507 (Thinking) | 51 | #260 (Qwen 3 235B A22B 2507) |
| 10 | Qwen 3 14B | 48.6 | #537 |
| 11 | Qwen 3.5 122B A10B | 47.6 | #173 |
| 12 | Qwen 3 4B 2507 (Thinking) | 46.8 | #538 (Qwen 3 4B 2507) |
| 13 | Kimi K2.5 | 44.4 | #144 |
| 14 | Qwen 3 Next 80B A3B (Thinking) | 44.2 | #320 (Qwen 3 Next 80B A3B) |
| 15 | Qwen 3.5 35B A3B | 42.8 | #256 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mera-lcs · How It Works · Data refreshed daily, snapshot 2026-10-20.