Models / claude-3-haiku-20240307
Anthropicclaude-3-haiku-20240307
9 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
- Anthropic
- Sources
- 2
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
1,248
Business, management and finance · rank 294 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,240 to 1,256
- Sample
- 13237 votes
- Configuration
- claude-3-haiku-20240307
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,216
Creative writing · rank 299 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,208 to 1,223
- Sample
- 16718 votes
- Configuration
- claude-3-haiku-20240307
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,253
Expert prompts · rank 272 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,242 to 1,264
- Sample
- 6336 votes
- Configuration
- claude-3-haiku-20240307
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,245
Instruction following · rank 298 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,240 to 1,251
- Sample
- 43031 votes
- Configuration
- claude-3-haiku-20240307
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,262
Overall · rank 304 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,258 to 1,265
- Sample
- 117701 votes
- Configuration
- claude-3-haiku-20240307
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,247
Writing, literature and language · rank 292 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,241 to 1,253
- Sample
- 29876 votes
- Configuration
- claude-3-haiku-20240307
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
15.0%
Requested-length error · rank 119 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- claude-3-haiku-20240307
- Measured
- 2 Oct 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.34
Style adherence · rank 224 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- claude-3-haiku-20240307
- Measured
- 2 Oct 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
31.9
Writing score · rank 259 of 370
- Unit
- score out of 100, higher is better
- Configuration
- claude-3-haiku-20240307
- Measured
- 2 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.
Compare claude-3-haiku-20240307 with
