Models / Command R+ (08-2024)
CohereCommand R+ (08-2024)
11 published results from 3 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
- 3
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
1,271
Business, management and finance · rank 266 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,254 to 1,288
- Sample
- 1132 votes
- Configuration
- Command R+ (08-2024)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,263
Creative writing · rank 243 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,248 to 1,278
- Sample
- 1474 votes
- Configuration
- Command R+ (08-2024)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,250
Expert prompts · rank 263 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,225 to 1,274
- Sample
- 524 votes
- Configuration
- Command R+ (08-2024)
- 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
Instruction following · rank 287 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,245 to 1,263
- Sample
- 4024 votes
- Configuration
- Command R+ (08-2024)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,276
Overall · rank 286 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,270 to 1,283
- Sample
- 9866 votes
- Configuration
- Command R+ (08-2024)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,277
Writing, literature and language · rank 252 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,266 to 1,288
- Sample
- 2672 votes
- Configuration
- Command R+ (08-2024)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
28.0%
Requested-length error · rank 243 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Command R+ (08-2024)
- Measured
- 10 Oct 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.34
Style adherence · rank 222 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Command R+ (08-2024)
- Measured
- 10 Oct 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
32.3
Writing score · rank 256 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Command R+ (08-2024)
- Measured
- 10 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.
95.0%
Answer rate · rank 91 of 108
- Unit
- % of documents, higher is better
- Configuration
- Command R+ (08-2024)
- 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.
6.9%
Hallucination rate · rank 30 of 108
- Unit
- % of summaries, lower is better
- Configuration
- Command R+ (08-2024)
- 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 Command R+ (08-2024) with
