1,316
Business, management and finance · rank 219 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,307 to 1,325
- Sample
- 4903 votes
- Configuration
- Llama 4 Scout
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,289
Creative writing · rank 213 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,278 to 1,299
- Sample
- 3731 votes
- Configuration
- Llama 4 Scout
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,309
Expert prompts · rank 220 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,293 to 1,324
- Sample
- 1518 votes
- Configuration
- Llama 4 Scout
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,299
Instruction following · rank 236 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,292 to 1,306
- Sample
- 7428 votes
- Configuration
- Llama 4 Scout
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,322
Overall · rank 238 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,317 to 1,326
- Sample
- 29673 votes
- Configuration
- Llama 4 Scout
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,305
Writing, literature and language · rank 216 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,297 to 1,313
- Sample
- 6666 votes
- Configuration
- Llama 4 Scout
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
44.9%
Irrelevance detection · rank 101 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
8.2%
Memory · rank 79 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
9.0%
Multi-turn tasks · rank 71 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
28.1%
Overall accuracy · rank 72 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- 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.
100.0%
Relevance detection · rank 1 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
89.4%
Single-turn calls (curated) · rank 8 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- 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.
74.7%
Single-turn calls (user-contributed) · rank 41 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- 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.
14.5%
Web search · rank 49 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-scout
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
19.0%
Requested-length error · rank 163 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Llama 4 Scout
- Measured
- 26 Oct 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.36
Style adherence · rank 127 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Llama 4 Scout
- Measured
- 26 Oct 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
26.7
Writing score · rank 293 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Llama 4 Scout
- Measured
- 26 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.
99.0%
Answer rate · rank 68 of 108
- Unit
- % of documents, higher is better
- Configuration
- Llama 4 Scout
- Measured
- 22 Sep 2026
- Not shown
- Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
7.7%
Hallucination rate · rank 38 of 108
- Unit
- % of summaries, lower is better
- Configuration
- Llama 4 Scout
- Measured
- 22 Sep 2026
- Not shown
- Not errors in open questions or other tasks: only summarisation, judged by Vectara's own model (HHEM-2.3), not by people, on news-style documents rather than your data.
