1,397
Business, management and finance · rank 122 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,388 to 1,407
- Sample
- 4105 votes
- Configuration
- Qwen3 30B A3B 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.
1,319
Creative writing · rank 182 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,308 to 1,330
- Sample
- 2932 votes
- Configuration
- Qwen3 30B A3B 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.
1,395
Expert prompts · rank 141 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,378 to 1,412
- Sample
- 1149 votes
- Configuration
- Qwen3 30B A3B 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.
1,366
Instruction following · rank 165 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,359 to 1,374
- Sample
- 5922 votes
- Configuration
- Qwen3 30B A3B 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.
1,383
Overall · rank 165 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,378 to 1,388
- Sample
- 23179 votes
- Configuration
- Qwen3 30B A3B 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.
1,342
Writing, literature and language · rank 178 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,333 to 1,350
- Sample
- 5022 votes
- Configuration
- Qwen3 30B A3B 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.
79.9%
Irrelevance detection · rank 59 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
74.8%
Irrelevance detection · rank 72 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
17.6%
Memory · rank 51 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
9.7%
Memory · rank 73 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
30.0%
Multi-turn tasks · rank 40 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
23.5%
Multi-turn tasks · rank 48 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
41.4%
Overall accuracy · rank 41 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- 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.
36.7%
Overall accuracy · rank 53 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- 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
- qwen3-30b-a3b-instruct-2507
- 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
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
85.8%
Single-turn calls (curated) · rank 37 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- 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.
88.9%
Single-turn calls (curated) · rank 9 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- 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.
77.9%
Single-turn calls (user-contributed) · rank 28 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- 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.
78.4%
Single-turn calls (user-contributed) · rank 26 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- 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.
22.5%
Web search · rank 40 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
17.5%
Web search · rank 46 of 109
- Unit
- % correct, higher is better
- Configuration
- qwen3-30b-a3b-instruct-2507
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
13.0%
Requested-length error · rank 103 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Qwen3 30B A3B Instruct 2507
- Measured
- 9 Oct 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.31
Style adherence · rank 302 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Qwen3 30B A3B Instruct 2507
- Measured
- 9 Oct 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
27.9
Writing score · rank 285 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Qwen3 30B A3B Instruct 2507
- Measured
- 9 Oct 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.
