List your company

Hallucination Evaluation on MMLU-Pro Law (test)

12.1HALL%GEMMA-2-9B
10.31222.38134.4546.519Jan 30, 2026

Evaluation results

MethodLinks
GEMMA-2-9Bmode=zero-shot, extraction_framework=DecompressionLM2026.0112.117515.4
QWEN2-7Bmode=zero-shot, extraction_framework=DecompressionLM2026.0112.117516.4
PHI-3-MINI-128Kmode=zero-shot, extraction_framework=DecompressionLM2026.0113.517318
PHI-3.5-MINImode=zero-shot, extraction_framework=DecompressionLM2026.0114.517117.8
PHI-3-MINI-4Kmode=zero-shot, extraction_framework=DecompressionLM2026.0118.516322.9
MISTRAL-NEMOmode=zero-shot, extraction_framework=DecompressionLM2026.0119.315920.4
NEO-7Bmode=zero-shot, extraction_framework=DecompressionLM2026.0122.215414.9
MINISTRAL-8Bmode=zero-shot, extraction_framework=DecompressionLM2026.0123.515025
DEEPSEEK-MATH-7Bmode=zero-shot, extraction_framework=DecompressionLM2026.0125.514927.9
MISTRAL-7Bmode=zero-shot, extraction_framework=DecompressionLM2026.0127.55827.3
QWEN2-1.5Bmode=zero-shot, extraction_framework=DecompressionLM2026.0127.814318.6
GRANITE-3.1-8Bmode=zero-shot, extraction_framework=DecompressionLM2026.012814418.4
LLAMA-3.1-8Bmode=zero-shot, extraction_framework=DecompressionLM2026.0128.114322.7
GRANITE-3.1-2Bmode=zero-shot, extraction_framework=DecompressionLM2026.0132.81318.6
DEEPSEEK-V2-LITEmode=zero-shot, extraction_framework=DecompressionLM2026.0132.813313.6
LLAMA-3-8Bmode=zero-shot, extraction_framework=DecompressionLM2026.0133.2133-8.8
QWEN2-0.5Bmode=zero-shot, extraction_framework=DecompressionLM2026.0134.212519.8
GRANITE-3.1-1Bmode=zero-shot, extraction_framework=DecompressionLM2026.0142.411429.4
GRANITE-3.1-3Bmode=zero-shot, extraction_framework=DecompressionLM2026.0144.710915.3
EXAONE-3.5-2.4Bmode=zero-shot, extraction_framework=DecompressionLM2026.0146.71068.9
LLAMA-3-SMAUGmode=zero-shot, extraction_framework=DecompressionLM2026.0156.886-14.4