GigaChat-20B-A3B: benchmark results
Provider: Other.
Aggregate Rating 1493 ± 37, rank #2466 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - ruModAr | 87.02 | EM (%) | 80.6 |
| MERA - CheGeKa | 31.84 | F1 (%) | 70.6 |
| MERA - USE | 33.43 | Grade, normalized (%) | 70.5 |
| MERA - ruHateSpeech | 77.74 | Accuracy (%) | 58.3 |
| MERA | 0.51 | Total score | 56.7 |
| MERA - ruTiE | 75.8 | Accuracy (%) | 56.7 |
| MERA - PARus | 84.2 | Accuracy (%) | 55.9 |
| MERA - MaMuRAMu | 74.06 | Accuracy (%) | 55.7 |
| MERA - ruHHH | 73.03 | Accuracy (%) | 53.3 |
| MERA - ruOpenBookQA | 83.25 | Accuracy (%) | 51.9 |
| MERA - ruDetox | 19.11 | Joint Score (%) | 48.8 |
| MERA - ruMMLU | 58.71 | Accuracy (%) | 48.1 |
Interactive version: theaggregate.ai/model?slug=gigachat-20b-a3b · How It Works · Data refreshed daily, snapshot 2026-11-08.