Models / phi-3-mini-4k-instruct
Microsoftphi-3-mini-4k-instruct
6 published results from 1 source. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.
- Provider
- Microsoft
- Sources
- 1
- Our benchmarks
- 0
- Price per million tokens
- Not listed on OpenRouter
Reported by others
1,112
Business, management and finance · rank 361 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,098 to 1,125
- Sample
- 2483 votes
- Configuration
- phi-3-mini-4k-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,073
Creative writing · rank 373 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,060 to 1,086
- Sample
- 2812 votes
- Configuration
- phi-3-mini-4k-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,140
Expert prompts · rank 330 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,121 to 1,160
- Sample
- 936 votes
- Configuration
- phi-3-mini-4k-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,113
Instruction following · rank 364 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,105 to 1,122
- Sample
- 7636 votes
- Configuration
- phi-3-mini-4k-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,128
Overall · rank 375 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,122 to 1,134
- Sample
- 20118 votes
- Configuration
- phi-3-mini-4k-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,093
Writing, literature and language · rank 370 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,082 to 1,103
- Sample
- 5207 votes
- Configuration
- phi-3-mini-4k-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
