Factuality Evaluation on HaluEval Sum (500 items)
63MC1 ScoreGPT-OSS-20B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-OSS-20BI(M)=3.48, Branch=mix2026.05 | 63 | 56.96 | |
| LLaMA-30BI(M)=0.13, Branch=early2026.05 | 50.6 | 49.84 | |
| TRACEBase Model=Gemma-3-1B, I(M)=6.54, Branch=mix2026.05 | 47.2 | 26.14 | |
| LLaMA-13BI(M)=0.16, Branch=early2026.05 | 47 | 49.01 | |
| LLaMA-7BI(M)=0.21, Branch=early2026.05 | 44.6 | 48.2 | |
| Mixtral-8×7BI(M)=1.30, Branch=mix2026.05 | 43.6 | 48.3 | |
| GPT-OSS-120BI(M)=5.66, Branch=mix2026.05 | 41 | 46.92 | |
| Ministral-3-14B-RI(M)=0.57, Branch=early2026.05 | 33.8 | 44.34 | |
| TRACEBase Model=Gemma-3-27B, I(M)=5.18, Branch=mix2026.05 | 32.2 | 20.41 | |
| DeepSeek-R1-Q-32BI(M)=1.18, Branch=mix2026.05 | 32.2 | 42.48 | |
| TRACEBase Model=Gemma-3-4B, I(M)=11.91, Branch=mix2026.05 | 31.6 | 18.37 | |
| Llama-3.3-70BI(M)=0.39, Branch=early2026.05 | 31.4 | 41.14 | |
| Gemma-3-1BI(M)=6.54, Branch=mix2026.05 | 30.2 | 40.79 | |
| TRACEBase Model=Phi-4-Reasoning, I(M)=0.27, Branch=early2026.05 | 30 | 10.83 | |
| Qwen3-30B-A3BI(M)=3.51, Branch=mix2026.05 | 28.8 | 41.41 | |
| Gemma-3-4BI(M)=11.91, Branch=mix2026.05 | 27.4 | 40.26 | |
| Gemma-3-27BI(M)=5.18, Branch=mix2026.05 | 26.6 | 39.33 | |
| Phi-4-ReasoningI(M)=0.27, Branch=early2026.05 | 26 | 41.11 | |
| Qwen3-14BI(M)=2.57, Branch=mix2026.05 | 24.2 | 38.27 | |
| TRACEBase Model=Mixtral-8×7B, I(M)=1.30, Branch=mix2026.05 | 19 | 6.19 | |
| TRACEBase Model=Qwen3-30B-A3B, I(M)=3.51, Branch=mix2026.05 | 16.4 | 7.66 | |
| TRACEBase Model=GPT-OSS-120B, I(M)=5.66, Branch=mix2026.05 | 15.4 | 6.51 | |
| TRACEBase Model=GPT-OSS-20B, I(M)=3.48, Branch=mix2026.05 | 13.6 | 5.03 | |
| TRACEBase Model=LLaMA-7B, I(M)=0.21, Branch=early2026.05 | 10.8 | 3.16 | |
| TRACEBase Model=Llama-3.3-70B, I(M)=0.39, Branch=early2026.05 | 9.8 | 6.7 | |
| TRACEBase Model=Ministral-3-14B-R, I(M)=0.57, Branch=early2026.05 | 8.8 | 3.81 | |
| TRACEBase Model=Qwen3-14B, I(M)=2.57, Branch=mix2026.05 | 7.8 | 3.08 | |
| TRACEBase Model=LLaMA-13B, I(M)=0.16, Branch=early2026.05 | 6.8 | 1.29 | |
| TRACEBase Model=DeepSeek-R1-Q-32B, I(M)=1.18, Branch=mix2026.05 | 3.8 | 1.94 | |
| TRACEBase Model=LLaMA-30B, I(M)=0.13, Branch=early2026.05 | 2 | 0.4 |