List your company

Polish Instruction Following on Open PL LLM Leaderboard

69.84Average ScoreMistral-Large-Instruct-2411
30.37240.618550.86561.1115Mar 12, 2026

Evaluation results

MethodLinks
Mistral-Large-Instruct-2411Parameters (B)=123.0, Evaluation=5-shot2026.0369.84
Meta-Llama-3.1-405B-Instruct-FP8Parameters (B)=405.0, Evaluation=5-shot2026.0369.44
Mistral-Large-Instruct-2407Parameters (B)=123.0, Evaluation=5-shot2026.0369.11
Qwen2.5-72B-InstructParameters (B)=72.7, Evaluation=5-shot2026.0367.92
QwQ-32B-PreviewParameters (B)=32.8, Evaluation=5-shot2026.0367.01
Llama-3.3-70B-InstructParameters (B)=70.6, Evaluation=5-shot2026.0366.4
Bielik-11B-v3.0-InstructParameters (B)=11.2, Evaluation=5-shot2026.0365.93
Qwen2-72B-InstructParameters (B)=72.7, Evaluation=5-shot2026.0365.87
Bielik-11B-v2.3-InstructParameters (B)=11.2, Evaluation=5-shot2026.0365.71
Bielik-11B-v2.2-InstructParameters (B)=11.2, Evaluation=5-shot2026.0365.57
Meta-Llama-3.1-70B-InstructParameters (B)=70.6, Evaluation=5-shot2026.0365.49
Bielik-11B-v2.1-InstructParameters (B)=11.2, Evaluation=5-shot2026.0365.45
Mixtral-8x22B-Instruct-v0.1Parameters (B)=141.0, Evaluation=5-shot2026.0365.23
Bielik-11B-v2.0-InstructParameters (B)=11.2, Evaluation=5-shot2026.0364.98
Meta-Llama-3-70B-InstructParameters (B)=70.6, Evaluation=5-shot2026.0364.45
Bielik-11B-v2.6-InstructParameters (B)=11.2, Evaluation=5-shot2026.0364.26
Qwen3-32BParameters (B)=32.8, Evaluation=5-shot2026.0364.24
Llama-4-Scout-17B-16E-InstructParameters (B)=109.0, Evaluation=5-shot2026.0364.21
Bielik-11B-v2.5-InstructParameters (B)=11.2, Evaluation=5-shot2026.0363.95
Mistral-Small-24B-Instruct-2501Parameters (B)=24.0, Evaluation=5-shot2026.0362.97
phi-4Parameters (B)=14.7, Evaluation=5-shot2026.0362.57
Bielik-Minitron-7B-v3.0-InstructParameters (B)=7.35, Evaluation=5-shot2026.0362.46
Qwen3-14BParameters (B)=14.8, Evaluation=5-shot2026.0362.24
gemma-3-12b-itParameters (B)=12.0, Evaluation=5-shot2026.0362.2
Mistral-Small-Instruct-2409Parameters (B)=22.2, Evaluation=5-shot2026.0361.41
Qwen2.5-32B-InstructParameters (B)=32.8, Evaluation=5-shot2026.0361.21
Qwen2.5-14B-InstructParameters (B)=14.8, Evaluation=5-shot2026.0359.91
aya-23-35BParameters (B)=35.0, Evaluation=5-shot2026.0356.37
Bielik-4.5B-v3.0-InstructParameters (B)=4.8, Evaluation=5-shot2026.0356.13
gemma-3-27b-itParameters (B)=27.0, Evaluation=5-shot2026.0355.92
Qwen3-8BParameters (B)=8.2, Evaluation=5-shot2026.0355.78
Qwen3-4BParameters (B)=4.0, Evaluation=5-shot2026.0355.49
Mistral-Nemo-Instruct-2407Parameters (B)=12.2, Evaluation=5-shot2026.0355.27
EuroLLM-22B-Instruct-PreviewParameters (B)=22.0, Evaluation=5-shot2026.0355.17
Qwen2.5-7B-InstructParameters (B)=7.6, Evaluation=5-shot2026.0354.93
EuroLLM-9B-InstructParameters (B)=9.0, Evaluation=5-shot2026.0350.07
GaMS-9B-InstructParameters (B)=9.0, Evaluation=5-shot2026.0348.78
Mistral-7B-Instruct-v0.3Parameters (B)=7.2, Evaluation=5-shot2026.0347.74
Apertus-8B-Instruct-2509Parameters (B)=8.0, Evaluation=5-shot2026.0347.27
Mistral-7B-Instruct-v0.2Parameters (B)=7.2, Evaluation=5-shot2026.0345.95
Bielik-7B-Instruct-v0.1Parameters (B)=7.2, Evaluation=5-shot2026.0344.7
gemma-2-9b-itParameters (B)=9.0, Evaluation=5-shot2026.0342.12
Qwen2.5-3B-InstructParameters (B)=3.0, Evaluation=5-shot2026.0341.23
Mistral-7B-Instruct-v0.1Parameters (B)=7.0, Evaluation=5-shot2026.0333.11
Qwen2.5-1.5B-InstructParameters (B)=1.5, Evaluation=5-shot2026.0331.89