ReflectionCoder-DS-33B: benchmark results
Provider: Other. Released 2024-05-28. Access: Open.
Unified ELO 1347 ± 1, rank #1276 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BigCodeBench | 42.4 | Pass@1 (%) | 65.9 |
| Open LLM Leaderboard - IFEval | 37.87 | Score | 37 |
| Open LLM Leaderboard - GPQA | 3.24 | Score | 29.4 |
| Open Chinese LLM - TruthfulQA MC | 49.97 | Accuracy (%) | 19 |
| Open LLM Leaderboard - MATH Level 5 | 3.02 | Score | 19 |
| Open LLM Leaderboard - BBH | 8.34 | Score | 17.9 |
| Open Chinese LLM - GSM8K | 22.14 | Accuracy (%) | 14.7 |
| Open Chinese LLM - ARC Challenge | 43.6 | Accuracy (%) | 12.2 |
| Open Chinese LLM - HellaSwag | 52.43 | Accuracy (%) | 11.3 |
| Open Chinese LLM - WinoGrande | 58.88 | Accuracy (%) | 10.2 |
| Open Chinese LLM - C-Eval Semantic | 50.82 | Accuracy (%) | 9.8 |
| Open LLM Leaderboard - MMLU-Pro | 2.24 | Score | 9.6 |
Interactive version: theaggregate.ai/model?slug=reflectioncoder-ds-33b · How It Works · Data refreshed daily, snapshot 2026-09-05.