List your company

Factuality Evaluation on HaluEval Sum (500 items)

63MC1 ScoreGPT-OSS-20B
-0.4416.0332.548.97May 18, 2026

Evaluation results

MethodLinks
GPT-OSS-20BI(M)=3.48, Branch=mix2026.056356.96
LLaMA-30BI(M)=0.13, Branch=early2026.0550.649.84
TRACEBase Model=Gemma-3-1B, I(M)=6.54, Branch=mix2026.0547.226.14
LLaMA-13BI(M)=0.16, Branch=early2026.054749.01
LLaMA-7BI(M)=0.21, Branch=early2026.0544.648.2
Mixtral-8×7BI(M)=1.30, Branch=mix2026.0543.648.3
GPT-OSS-120BI(M)=5.66, Branch=mix2026.054146.92
Ministral-3-14B-RI(M)=0.57, Branch=early2026.0533.844.34
TRACEBase Model=Gemma-3-27B, I(M)=5.18, Branch=mix2026.0532.220.41
DeepSeek-R1-Q-32BI(M)=1.18, Branch=mix2026.0532.242.48
TRACEBase Model=Gemma-3-4B, I(M)=11.91, Branch=mix2026.0531.618.37
Llama-3.3-70BI(M)=0.39, Branch=early2026.0531.441.14
Gemma-3-1BI(M)=6.54, Branch=mix2026.0530.240.79
TRACEBase Model=Phi-4-Reasoning, I(M)=0.27, Branch=early2026.053010.83
Qwen3-30B-A3BI(M)=3.51, Branch=mix2026.0528.841.41
Gemma-3-4BI(M)=11.91, Branch=mix2026.0527.440.26
Gemma-3-27BI(M)=5.18, Branch=mix2026.0526.639.33
Phi-4-ReasoningI(M)=0.27, Branch=early2026.052641.11
Qwen3-14BI(M)=2.57, Branch=mix2026.0524.238.27
TRACEBase Model=Mixtral-8×7B, I(M)=1.30, Branch=mix2026.05196.19
TRACEBase Model=Qwen3-30B-A3B, I(M)=3.51, Branch=mix2026.0516.47.66
TRACEBase Model=GPT-OSS-120B, I(M)=5.66, Branch=mix2026.0515.46.51
TRACEBase Model=GPT-OSS-20B, I(M)=3.48, Branch=mix2026.0513.65.03
TRACEBase Model=LLaMA-7B, I(M)=0.21, Branch=early2026.0510.83.16
TRACEBase Model=Llama-3.3-70B, I(M)=0.39, Branch=early2026.059.86.7
TRACEBase Model=Ministral-3-14B-R, I(M)=0.57, Branch=early2026.058.83.81
TRACEBase Model=Qwen3-14B, I(M)=2.57, Branch=mix2026.057.83.08
TRACEBase Model=LLaMA-13B, I(M)=0.16, Branch=early2026.056.81.29
TRACEBase Model=DeepSeek-R1-Q-32B, I(M)=1.18, Branch=mix2026.053.81.94
TRACEBase Model=LLaMA-30B, I(M)=0.13, Branch=early2026.0520.4