List your company

Tool-use Factuality Evaluation on BFCL Task

76Factuality ScoreGPT-OSS-120B
4.2422.8741.560.13May 1, 2026

Evaluation results

MethodLinks
GPT-OSS-120BExperimental Setup=Optimized2026.0576129
Qwen-3-30B-ITExperimental Setup=Optimized2026.0574148
GPT-OSS-120BExperimental Setup=Always Tool2026.0573328
Gemma3-27B-ITExperimental Setup=Optimized2026.0573103
Qwen-3-30B-ITExperimental Setup=Always Tool2026.0571328
Mistral3.1-24B-ITExperimental Setup=Optimized2026.0571135
Qwen-3-30B-ITExperimental Setup=Self-decided2026.0567351
GPT-OSS-120BExperimental Setup=Self-decided2026.0566196
Gemma3-27B-ITExperimental Setup=Always Tool2026.0566328
Mistral3.1-24B-ITExperimental Setup=Always Tool2026.0566328
Llama3.2-3B-ITExperimental Setup=Optimized2026.0566160
GPT-OSS-120BExperimental Setup=LNE2026.0565207
Qwen3-30B-A3BExperimental Setup=Optimized2026.0564146
Llama3.2-3B-ITExperimental Setup=Always Tool2026.0563328
Gemma3-27B-ITExperimental Setup=Self-decided2026.0562360
Gemma3-27B-ITExperimental Setup=LNE2026.0561218
Qwen3-30B-A3BExperimental Setup=Always Tool2026.0560328
Mistral3.1-24B-ITExperimental Setup=Self-decided2026.0560302
Qwen-3-30B-ITExperimental Setup=LNE2026.0558206
Llama3.2-3B-ITExperimental Setup=Self-decided2026.0558346
Llama3.2-3B-ITExperimental Setup=LNE2026.0558263
Mistral3.1-24B-ITExperimental Setup=LNE2026.0557240
Qwen3-30B-A3BExperimental Setup=LNE2026.0556264
GPT-OSS-120BExperimental Setup=LUEx2026.0555130
Qwen3-30B-A3BExperimental Setup=Self-decided2026.0552261
Qwen-3-30B-ITExperimental Setup=LUEx2026.0551138
Gemma3-27B-ITExperimental Setup=LUEx2026.055083
Mistral3.1-24B-ITExperimental Setup=LUEx2026.0546143
Qwen3-30B-A3BExperimental Setup=LUEx2026.0542156
Gemma3-27B-ITExperimental Setup=No Tool2026.05420
Llama3.2-3B-ITExperimental Setup=LUEx2026.0542153
GPT-OSS-120BExperimental Setup=No Tool2026.05360
Mistral3.1-24B-ITExperimental Setup=No Tool2026.05300
Qwen-3-30B-ITExperimental Setup=No Tool2026.05290
Qwen3-30B-A3BExperimental Setup=No Tool2026.05200
Llama3.2-3B-ITExperimental Setup=No Tool2026.05170
Llama3.2-3B-ITExperimental Setup=LUEx,d2026.0516161
Qwen3-30B-A3BExperimental Setup=LUEx,d2026.0515154
Qwen-3-30B-ITExperimental Setup=LUEx,d2026.0513134
Mistral3.1-24B-ITExperimental Setup=LUEx,d2026.0513132
GPT-OSS-120BExperimental Setup=LUEx,d2026.0512123
Gemma3-27B-ITExperimental Setup=LUEx,d2026.05767