Models / llama-3.1-405b-instruct-fp8
Metallama-3.1-405b-instruct-fp8
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
- Meta
- Sources
- 1
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
1,314
Business, management and finance · rank 222 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,306 to 1,323
- Sample
- 6667 votes
- Configuration
- llama-3.1-405b-instruct-fp8
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,305
Creative writing · rank 202 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,297 to 1,312
- Sample
- 8948 votes
- Configuration
- llama-3.1-405b-instruct-fp8
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,325
Expert prompts · rank 207 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,313 to 1,336
- Sample
- 3123 votes
- Configuration
- llama-3.1-405b-instruct-fp8
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,315
Instruction following · rank 219 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,310 to 1,320
- Sample
- 23585 votes
- Configuration
- llama-3.1-405b-instruct-fp8
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,334
Overall · rank 219 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,330 to 1,337
- Sample
- 59656 votes
- Configuration
- llama-3.1-405b-instruct-fp8
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,316
Writing, literature and language · rank 209 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,310 to 1,322
- Sample
- 15999 votes
- Configuration
- llama-3.1-405b-instruct-fp8
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
