Ukrainian Legal Text Benchmark (EDRSR subset): leaderboard
Tokenizer fertility varies 1.6x across foundation models on Ukrainian legal text, yet this cost-critical dimension is absent from model selection practice. We benchmark seven models from five providers on 273 validated court decisions from Ukraine's state registry (EDRSR), measuring tokenizer fertility and zero-shot performance on three tasks. Four findings emerge. (1) Qwen 3 models consume 60% mo
Metric: 3-task Composite (self-reported). Source: benchmarklist.com. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nemotron 3 Super | 83.1 | #335 |
| 2 | Nova Pro | 82.7 | #569 |
| 3 | Llama 3.3 70B | 81.6 | #579 |
| 4 | Mistral Large 3 | 81.1 | #401 |
| 5 | Llama 4 Maverick | 79.6 | #464 |
| 6 | Qwen 3 235B A22B | 79.2 | #313 |
| 7 | Qwen 3 32B | 77.8 | #443 |
Interactive version: theaggregate.ai/benchmark?slug=ukrainian-legal-text-benchmark-edrsr-subset · How It Works · Data refreshed daily, snapshot 2026-10-20.