| eval-result:human-eval.llama-3-1-405b.001 | eval-result:human-eval.llama-3-1-405b.001 | benchmarks |
| eval-result:human-eval.llama-4-405b.001 | eval-result:human-eval.llama-4-405b.001 | benchmarks |
| eval-result:mmlu.llama-3-1-405b.001 | eval-result:mmlu.llama-3-1-405b.001 | benchmarks |
| eval-result:mmlu.llama-4-405b.001 | eval-result:mmlu.llama-4-405b.001 | benchmarks |
| eval-result:swe-bench-verified.llama-4-405b.001 | eval-result:swe-bench-verified.llama-4-405b.001 | benchmarks |
| eval-result:swe-bench.llama-3-1-405b.001 | eval-result:swe-bench.llama-3-1-405b.001 | benchmarks |