T-lite-0.1: benchmark results
Provider: T-Bank.
Aggregate Rating 1453 ± 37, rank #3665 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA - RWSD | 61.15 | Accuracy (%) | 71.4 |
| MERA - ruHumanEval | 26.65 | pass@1 (%) | 71.1 |
| MERA - ruCodeEval | 25.24 | pass@1 (%) | 68.1 |
| MERA - CheGeKa | 30.49 | F1 (%) | 67.8 |
| MERA - MultiQ | 48.2 | F1 (%) | 63 |
| MERA - LCS | 14.8 | Accuracy (%) | 61 |
| MERA - ruModAr | 66.92 | EM (%) | 59.2 |
| MERA | 0.51 | Total score | 55.7 |
| MERA - PARus | 81.4 | Accuracy (%) | 51.2 |
| MERA - RCB | 53.65 | Accuracy (%) | 51 |
| MERA - ruHateSpeech | 73.21 | Accuracy (%) | 49 |
| MERA - ruWorldTree | 88.76 | Accuracy (%) | 47.1 |
Interactive version: theaggregate.ai/model?slug=t-lite-0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.