Bielik-11B-v2.1-Instruct — benchmark results
SpeakLeash's Polish 11B instruct fine-tune of the Bielik v2 base (depth-upscaled Mistral 7B v0.2), sibling variant to v2.2 (August 2024). Provider: SpeakLeash. Released 2024-08-26. Access: Open.
Unified ELO 1510 ± 21, rank #765 of 1776 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - RAG | 76.79 | Average RAG Score (%) | 99.5 |
| MT-Bench PL - Writing | 9.5 | Judge Score (0-10) | 94.9 |
| MT-Bench PL - Roleplay | 9.45 | Judge Score (0-10) | 93.9 |
| Open PL LLM - Multiple Choice | 62.88 | Average Multiple-Choice Score (%) | 92.3 |
| Open PL LLM Leaderboard | 65.45 | Average Score (%) | 92 |
| Open PL LLM - Generative | 67.42 | Average Generative Score (%) | 86.7 |
| Open LLM Leaderboard - GPQA | 11.63 | Score | 83.4 |
| LLMZSZL Leaderboard | 57.52 | Score | 79.6 |
| Open LLM Leaderboard - MATH Level 5 | 26.66 | Score | 79.3 |
| Open LLM Leaderboard - BBH | 36.29 | Score | 74.4 |
| Polish EQ-Bench | 66.27 | EQ-Bench Score | 72.3 |
| MT-Bench PL - Reasoning | 6.25 | Judge Score (0-10) | 66.3 |
Interactive version: theaggregate.ai/model?slug=bielik-11b-v2-1-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.