Models / c4ai-aya-expanse-32b
Coherec4ai-aya-expanse-32b
8 published results from 2 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.
- Provider
- Cohere
- Sources
- 2
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
1,268
Business, management and finance · rank 274 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,257 to 1,279
- Sample
- 3115 votes
- Configuration
- c4ai-aya-expanse-32b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,228
Creative writing · rank 288 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,217 to 1,238
- Sample
- 3853 votes
- Configuration
- c4ai-aya-expanse-32b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,267
Expert prompts · rank 260 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,253 to 1,281
- Sample
- 1764 votes
- Configuration
- c4ai-aya-expanse-32b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,249
Instruction following · rank 292 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,243 to 1,256
- Sample
- 11265 votes
- Configuration
- c4ai-aya-expanse-32b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,267
Overall · rank 299 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,262 to 1,272
- Sample
- 27124 votes
- Configuration
- c4ai-aya-expanse-32b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,254
Writing, literature and language · rank 284 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,246 to 1,262
- Sample
- 7297 votes
- Configuration
- c4ai-aya-expanse-32b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
99.8%
Answer rate · rank 34 of 108
- Unit
- % of documents, higher is better
- Configuration
- c4ai-aya-expanse-32b
- 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.
10.9%
Hallucination rate · rank 70 of 108
- Unit
- % of summaries, lower is better
- Configuration
- c4ai-aya-expanse-32b
- 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.
Compare c4ai-aya-expanse-32b with
