Tool-use Factuality Evaluation on Entity Task
88Factuality ScoreQwen3-30B-A3B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-30B-A3BExperimental Setup=Optimized2026.05 | 88 | 252 | |
| Qwen-3-30B-ITExperimental Setup=Optimized2026.05 | 87 | 284 | |
| Llama3.2-3B-ITExperimental Setup=Optimized2026.05 | 87 | 249 | |
| Gemma3-27B-ITExperimental Setup=Optimized2026.05 | 85 | 297 | |
| Mistral3.1-24B-ITExperimental Setup=Optimized2026.05 | 85 | 345 | |
| GPT-OSS-120BExperimental Setup=Optimized2026.05 | 83 | 300 | |
| Qwen-3-30B-ITExperimental Setup=Always Tool2026.05 | 82 | 500 | |
| Qwen-3-30B-ITExperimental Setup=Self-decided2026.05 | 82 | 452 | |
| Qwen3-30B-A3BExperimental Setup=Self-decided2026.05 | 81 | 342 | |
| Qwen3-30B-A3BExperimental Setup=LNE2026.05 | 81 | 329 | |
| Qwen-3-30B-ITExperimental Setup=LNE2026.05 | 81 | 339 | |
| Qwen-3-30B-ITExperimental Setup=LUEx,d2026.05 | 81 | 271 | |
| Mistral3.1-24B-ITExperimental Setup=Always Tool2026.05 | 81 | 500 | |
| Qwen3-30B-A3BExperimental Setup=Always Tool2026.05 | 80 | 500 | |
| Gemma3-27B-ITExperimental Setup=Always Tool2026.05 | 80 | 500 | |
| Gemma3-27B-ITExperimental Setup=Self-decided2026.05 | 80 | 462 | |
| Mistral3.1-24B-ITExperimental Setup=LUEx,d2026.05 | 80 | 263 | |
| Llama3.2-3B-ITExperimental Setup=Always Tool2026.05 | 80 | 500 | |
| Qwen3-30B-A3BExperimental Setup=LUEx2026.05 | 79 | 249 | |
| Qwen-3-30B-ITExperimental Setup=LUEx2026.05 | 79 | 306 | |
| Mistral3.1-24B-ITExperimental Setup=Self-decided2026.05 | 79 | 172 | |
| Llama3.2-3B-ITExperimental Setup=LNE2026.05 | 79 | 429 | |
| GPT-OSS-120BExperimental Setup=Always Tool2026.05 | 78 | 500 | |
| GPT-OSS-120BExperimental Setup=LNE2026.05 | 78 | 351 | |
| Qwen3-30B-A3BExperimental Setup=LUEx,d2026.05 | 78 | 248 | |
| Gemma3-27B-ITExperimental Setup=LUEx,d2026.05 | 78 | 308 | |
| Mistral3.1-24B-ITExperimental Setup=LNE2026.05 | 78 | 279 | |
| Llama3.2-3B-ITExperimental Setup=LUEx2026.05 | 78 | 383 | |
| Llama3.2-3B-ITExperimental Setup=LUEx,d2026.05 | 78 | 354 | |
| GPT-OSS-120BExperimental Setup=LUEx2026.05 | 77 | 341 | |
| Mistral3.1-24B-ITExperimental Setup=LUEx2026.05 | 77 | 267 | |
| GPT-OSS-120BExperimental Setup=LUEx,d2026.05 | 75 | 293 | |
| Gemma3-27B-ITExperimental Setup=LNE2026.05 | 75 | 292 | |
| Gemma3-27B-ITExperimental Setup=LUEx2026.05 | 75 | 284 | |
| Llama3.2-3B-ITExperimental Setup=Self-decided2026.05 | 74 | 340 | |
| GPT-OSS-120BExperimental Setup=Self-decided2026.05 | 73 | 152 | |
| Mistral3.1-24B-ITExperimental Setup=No Tool2026.05 | 72 | 0 | |
| Qwen3-30B-A3BExperimental Setup=No Tool2026.05 | 70 | 0 | |
| Qwen-3-30B-ITExperimental Setup=No Tool2026.05 | 68 | 0 | |
| GPT-OSS-120BExperimental Setup=No Tool2026.05 | 61 | 0 | |
| Gemma3-27B-ITExperimental Setup=No Tool2026.05 | 60 | 0 | |
| Llama3.2-3B-ITExperimental Setup=No Tool2026.05 | 56 | 0 |