76.5%
Irrelevance detection · rank 67 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
6.0%
Memory · rank 86 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
11.0%
Multi-turn tasks · rank 65 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
28.4%
Overall accuracy · rank 71 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not a neutral average: the weighting is BFCL's. Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
81.2%
Relevance detection · rank 41 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
82.9%
Single-turn calls (curated) · rank 58 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
74.6%
Single-turn calls (user-contributed) · rank 43 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
2.5%
Web search · rank 71 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-1.7b (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
32.0%
Requested-length error · rank 263 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- qwen3-1.7b (no reasoning)
- Measured
- 13 Sep 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
26.0%
Requested-length error · rank 233 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- qwen3-1.7b (thinking reasoning)
- Measured
- 13 Sep 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.38
Style adherence · rank 58 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- qwen3-1.7b (no reasoning)
- Measured
- 13 Sep 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
0.37
Style adherence · rank 97 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- qwen3-1.7b (thinking reasoning)
- Measured
- 13 Sep 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
12.2
Writing score · rank 359 of 370
- Unit
- score out of 100, higher is better
- Configuration
- qwen3-1.7b (no reasoning)
- Measured
- 13 Sep 2025
- Not shown
- Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
18.8
Writing score · rank 341 of 370
- Unit
- score out of 100, higher is better
- Configuration
- qwen3-1.7b (thinking reasoning)
- Measured
- 13 Sep 2025
- Not shown
- Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
