ReflectionCoder-CL-34B: benchmark results
Provider: Other. Released 2024-05-28. Access: Open.
Unified ELO 1357 ± 1, rank #1255 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 10.4 | Score | 52.2 |
| BigCodeBench | 37.7 | Pass@1 (%) | 47.2 |
| Open LLM Leaderboard - IFEval | 40.08 | Score | 40 |
| Open LLM Leaderboard - BBH | 14.26 | Score | 22.9 |
| Open LLM Leaderboard - MATH Level 5 | 3.32 | Score | 20.2 |
| Open Chinese LLM - GSM8K | 22.82 | Accuracy (%) | 15.6 |
| Open Chinese LLM - TruthfulQA MC | 49.24 | Accuracy (%) | 15.1 |
| Open LLM Leaderboard - MMLU-Pro | 4.71 | Score | 11.9 |
| Open Chinese LLM - ARC Challenge | 41.55 | Accuracy (%) | 9.5 |
| Open Chinese LLM - HellaSwag | 50.41 | Accuracy (%) | 8.3 |
| Open Chinese LLM - WinoGrande | 57.3 | Accuracy (%) | 8.2 |
| Open Chinese LLM Leaderboard | 43.12 | Average Score (%) | 7.4 |
Interactive version: theaggregate.ai/model?slug=reflectioncoder-cl-34b · How It Works · Data refreshed daily, snapshot 2026-09-05.