codellama CodeLlama-34B-Instruct-hf (FP16): benchmark results
Provider: Meta.
Aggregate Rating 1243 ± 19, rank #9305 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 41 | Accuracy (%) | 97.2 |
| MMLU-by-task - Abstract Algebra | 36 | Accuracy (%) | 91.7 |
| MMLU-by-task - High School Mathematics | 31.11 | Accuracy (%) | 83.3 |
| MMLU-by-task - Elementary Mathematics | 30.42 | Accuracy (%) | 59.1 |
| MMLU-by-task - High School Chemistry | 36.45 | Accuracy (%) | 58.3 |
| MMLU-by-task - High School Physics | 31.13 | Accuracy (%) | 56.1 |
| MMLU-by-task - TruthfulQA MC1 | 29.01 | Accuracy (%) | 52.7 |
| MMLU-by-task - Jurisprudence | 53.7 | Accuracy (%) | 52.6 |
| MMLU-by-task - Formal Logic | 30.95 | Accuracy (%) | 52.2 |
| MMLU-by-task - Public Relations | 52.73 | Accuracy (%) | 48.8 |
| MMLU-by-task - Virology | 40.36 | Accuracy (%) | 48.6 |
| MMLU-by-task - High School Computer Science | 42 | Accuracy (%) | 47.9 |
Interactive version: theaggregate.ai/model?slug=codellama-codellama-34b-instruct-hf-fp16 · How It Works · Data refreshed daily, snapshot 2026-11-08.