Models / oasst-pythia-12b
Openassistantoasst-pythia-12b
5 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
- Openassistant
- Sources
- 1
- Our benchmarks
- 0
- Price per million tokens
- Not listed on OpenRouter
Reported by others
960
Business, management and finance · rank 394 of 402
- Unit
- Arena rating, higher is better
- Range
- 930 to 991
- Sample
- 454 votes
- Configuration
- oasst-pythia-12b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,013
Creative writing · rank 394 of 407
- Unit
- Arena rating, higher is better
- Range
- 992 to 1,033
- Sample
- 1094 votes
- Configuration
- oasst-pythia-12b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
988
Instruction following · rank 401 of 409
- Unit
- Arena rating, higher is better
- Range
- 972 to 1,004
- Sample
- 1744 votes
- Configuration
- oasst-pythia-12b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,024
Overall · rank 402 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,013 to 1,034
- Sample
- 6310 votes
- Configuration
- oasst-pythia-12b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,013
Writing, literature and language · rank 397 of 408
- Unit
- Arena rating, higher is better
- Range
- 995 to 1,031
- Sample
- 1408 votes
- Configuration
- oasst-pythia-12b
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
