Yi-Coder-9B-Chat: benchmark results
01.AI's Yi-Coder-9B-Chat, a code-focused chat model fine-tuned from Yi-Coder-9B, supporting 52 programming languages with up to 128K context. Provider: 01.AI. Released 2024-09-05. Access: Open.
Aggregate Rating 1388 ± 13, rank #1262 of 1656 rated models, from 86 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA Code - YABLoCo | 13.46 | pass@1 (%) | 93.8 |
| MERA - ruHumanEval | 41.4 | pass@1 (%) | 81.8 |
| MERA - ruCodeEval | 38.35 | pass@1 (%) | 79 |
| Open Korean LLM - Ko-IFEval | 37.64 | Strict accuracy, prompt/instruction mean (%) | 78.9 |
| XRepoTest - Ruby - Line Coverage | 9.37 | Focal line coverage (%; of all focal functions) | 76.9 |
| MERA - BPS | 98.5 | Accuracy (%) | 76.2 |
| MERA - RWSD | 61.54 | Accuracy (%) | 73.8 |
| MERA - LCS | 16.6 | Accuracy (%) | 68.3 |
| MERA Code - JavaTestGen | 22.91 | pass@1 (%) | 66.9 |
| RoundTripCodeEval - Huffman Coding | 1.87 | Mean of exact match, edit similarity and pass@5 (%) over the | 64.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 27.52 | Exact match, flexible extract (%) | 61.7 |
| MERA Code - ruCodeEval | 35 | pass@1 (%) | 60 |
Interactive version: theaggregate.ai/model?slug=yi-coder-9b-chat · How It Works · Data refreshed daily, snapshot 2026-10-20.