Models / phi-3-medium-4k-instruct
Microsoftphi-3-medium-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
1,179
Business, management and finance · rank 333 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,166 to 1,191
- Sample
- 2847 votes
- Configuration
- phi-3-medium-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.
1,150
Creative writing · rank 337 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,139 to 1,161
- Sample
- 3735 votes
- Configuration
- phi-3-medium-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.
1,205
Expert prompts · rank 301 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,188 to 1,223
- Sample
- 1091 votes
- Configuration
- phi-3-medium-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.
1,178
Instruction following · rank 335 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,170 to 1,185
- Sample
- 9385 votes
- Configuration
- phi-3-medium-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.
1,198
Overall · rank 336 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,193 to 1,203
- Sample
- 25055 votes
- Configuration
- phi-3-medium-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.
1,173
Writing, literature and language · rank 333 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,164 to 1,182
- Sample
- 6655 votes
- Configuration
- phi-3-medium-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.
