WizardCoder-15B-V1.0: benchmark results
Provider: WizardLMTeam. Released 2023-06-14. Access: Open.
Aggregate Rating 1193 ± 13, rank #1574 of 1640 rated models, from 80 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 34 | Accuracy (%) | 82 |
| EffiBench - NET | 2.84 | Normalized Execution Time | 81.7 |
| MMLU-by-task - College Mathematics | 36 | Accuracy (%) | 80.2 |
| BigCode Models Leaderboard | 58.1 | HumanEval Python Pass@1 (%) | 74.6 |
| MMLU-by-task - High School Mathematics | 28.15 | Accuracy (%) | 61.8 |
| InfiBench | 41.01 | Score (%) | 60 |
| EffiBench - NMU | 1.91 | Normalized Memory Usage | 58.5 |
| MMLU-by-task - Econometrics | 28.95 | Accuracy (%) | 55.2 |
| MMLU-by-task - College Physics | 25.49 | Accuracy (%) | 53.2 |
| EvalPlus (HumanEval+ & MBPP+) | 52.4 | Pass@1 avg (%) | 48.8 |
| MMLU-by-task - Elementary Mathematics | 28.31 | Accuracy (%) | 47.9 |
| CodeEditorBench Plus - Code Requirement Switch (Zero-shot) | 6.7 | pass@1 (%, greedy decoding, zero-shot, CodeEditorBench_Plus) | 44.4 |
Interactive version: theaggregate.ai/model?slug=wizardcoder-15b-v1-0 · How It Works · Data refreshed daily, snapshot 2026-10-13.