1,431
Overall · rank 92 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,429 to 1,434
- Sample
- 66540 votes
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 25 Sep 2026
- Not shown
- Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
1,432
Business, management and finance · rank 81 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,427 to 1,437
- Sample
- 18230 votes
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,378
Creative writing · rank 114 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,372 to 1,383
- Sample
- 13819 votes
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,448
Expert prompts · rank 90 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,440 to 1,455
- Sample
- 6405 votes
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,414
Instruction following · rank 100 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,410 to 1,419
- Sample
- 27749 votes
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,422
Overall · rank 110 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,420 to 1,425
- Sample
- 97815 votes
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,396
Writing, literature and language · rank 101 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,392 to 1,401
- Sample
- 22059 votes
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
81.7%
Irrelevance detection · rank 50 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
78.9%
Irrelevance detection · rank 65 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
23.9%
Memory · rank 35 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
19.4%
Memory · rank 46 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
45.4%
Multi-turn tasks · rank 21 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
44.6%
Multi-turn tasks · rank 23 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
48.0%
Overall accuracy · rank 31 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (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.
52.1%
Overall accuracy · rank 23 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- 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.
87.5%
Relevance detection · rank 27 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
93.8%
Relevance detection · rank 8 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
37.4%
Single-turn calls (curated) · rank 104 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (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.
90.3%
Single-turn calls (curated) · rank 2 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- 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.
68.9%
Single-turn calls (user-contributed) · rank 64 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (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.
78.7%
Single-turn calls (user-contributed) · rank 19 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- 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.
54.0%
Web search · rank 25 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
50.5%
Web search · rank 26 of 109
- Unit
- % correct, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507 (bfcl prompt)
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
15.0%
Requested-length error · rank 119 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 21 Sep 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.36
Style adherence · rank 124 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 21 Sep 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
49.0
Writing score · rank 164 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Qwen3 235B A22B Instruct 2507
- Measured
- 21 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.
