List your company

Tool-use Factuality Evaluation on InvivoQuery

78Factuality ScoreQwen3-30B-A3B
23.9237.965266.04May 1, 2026

Evaluation results

MethodLinks
Qwen3-30B-A3BExperimental Setup=Optimized2026.0578239
Mistral3.1-24B-ITExperimental Setup=Optimized2026.0572238
GPT-OSS-120BExperimental Setup=Optimized2026.0571235
Qwen-3-30B-ITExperimental Setup=Optimized2026.0571313
Gemma3-27B-ITExperimental Setup=Optimized2026.0567259
Qwen3-30B-A3BExperimental Setup=Always Tool2026.0565500
Qwen3-30B-A3BExperimental Setup=LNE2026.0563371
Qwen-3-30B-ITExperimental Setup=Always Tool2026.0562500
Qwen-3-30B-ITExperimental Setup=LNE2026.0561465
Llama3.2-3B-ITExperimental Setup=Optimized2026.0561251
Qwen3-30B-A3BExperimental Setup=LUEx2026.0560176
GPT-OSS-120BExperimental Setup=Always Tool2026.0559500
GPT-OSS-120BExperimental Setup=LNE2026.0559442
Qwen3-30B-A3BExperimental Setup=LUEx,d2026.0559177
Gemma3-27B-ITExperimental Setup=Always Tool2026.0559500
Mistral3.1-24B-ITExperimental Setup=LNE2026.0559478
Qwen3-30B-A3BExperimental Setup=No Tool2026.05580
Gemma3-27B-ITExperimental Setup=LNE2026.0558469
Mistral3.1-24B-ITExperimental Setup=Always Tool2026.0558500
GPT-OSS-120BExperimental Setup=LUEx,d2026.0557163
GPT-OSS-120BExperimental Setup=Self-decided2026.0556433
GPT-OSS-120BExperimental Setup=LUEx2026.0556164
Gemma3-27B-ITExperimental Setup=LUEx2026.0556358
Gemma3-27B-ITExperimental Setup=LUEx,d2026.0556344
Qwen-3-30B-ITExperimental Setup=LUEx2026.0555269
Mistral3.1-24B-ITExperimental Setup=No Tool2026.05550
Mistral3.1-24B-ITExperimental Setup=LUEx,d2026.055593
Qwen-3-30B-ITExperimental Setup=LUEx,d2026.0554250
Mistral3.1-24B-ITExperimental Setup=Self-decided2026.0554270
Mistral3.1-24B-ITExperimental Setup=LUEx2026.0554112
GPT-OSS-120BExperimental Setup=No Tool2026.05530
Gemma3-27B-ITExperimental Setup=No Tool2026.05500
Llama3.2-3B-ITExperimental Setup=Always Tool2026.0550500
Llama3.2-3B-ITExperimental Setup=LNE2026.0550465
Llama3.2-3B-ITExperimental Setup=LUEx2026.0548237
Llama3.2-3B-ITExperimental Setup=LUEx,d2026.0548211
Qwen-3-30B-ITExperimental Setup=No Tool2026.05460
Llama3.2-3B-ITExperimental Setup=No Tool2026.05450
Llama3.2-3B-ITExperimental Setup=Self-decided2026.05441,376
Gemma3-27B-ITExperimental Setup=Self-decided2026.0542326
Qwen3-30B-A3BExperimental Setup=Self-decided2026.0541235
Qwen-3-30B-ITExperimental Setup=Self-decided2026.0526458