CodeBooga-34B-v0.1: benchmark results
oobabooga's CodeBooga 34B, a BlockMerge Gradient merge of Phind-CodeLlama-34B-v2 and WizardCoder-Python-34B-V1.0 for coding tasks. Provider: oobabooga. Released 2023-10-19. Access: Open.
Aggregate Rating 1353 ± 22, rank #1378 of 1656 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 43.1 | Score | 71.1 |
| Open LLM Leaderboard - IFEval | 52.5 | Score | 62.5 |
| Open LLM Leaderboard v1 - GSM8K | 37.23 | Accuracy (%) (5-shot) | 52.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.12 | MC2 (%) (0-shot) | 39.9 |
| Open LLM Leaderboard v1 - MMLU | 54.4 | Accuracy (%) (5-shot) | 33.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 55.29 | Normalized accuracy (%) (25-shot) | 33.1 |
| Open LLM Leaderboard v1 - HellaSwag | 77.6 | Normalized accuracy (%) (10-shot) | 31.3 |
| Open LLM Leaderboard v1 - WinoGrande | 71.9 | Accuracy (%) (5-shot) | 27.7 |
| Open LLM Leaderboard - MMLU-Pro | 23.6 | Score | 24.2 |
| Open LLM Leaderboard - MATH Level 5 | 3.93 | Score | 22.6 |
| Open Chinese LLM - GSM8K | 28.35 | Accuracy (%) | 21.4 |
| Open Chinese LLM - HellaSwag | 54.28 | Accuracy (%) | 20.4 |
Interactive version: theaggregate.ai/model?slug=codebooga-34b-v0-1 · How It Works · Data refreshed daily, snapshot 2026-10-20.