Yi-Coder-9B: benchmark results

Provider: 01.AI. Released 2024-08-15. Access: Open.

Unified ELO 1393 ± 1, rank #1166 of 1392 rated models, from 34 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Beyond Pass Rate23.6Correctness (%)100
MERA - ruHumanEval29.33pass@1 (%)73.6
ShaderMatch14.72Clone Match Rate (%)71.4
MERA - BPS97.7Accuracy (%)69.7
MERA - ruCodeEval25.85pass@1 (%)69.4
MERA - LCS14.6Accuracy (%)59.6
MERA - RWSD55Accuracy (%)43.1
Open Chinese LLM - C-Eval Semantic63.31Accuracy (%)32.9
MERA - RCB50.46Accuracy (%)32.1
MERA - MathLogicQA37.88Accuracy (%)31.8
MERA - ruHHH59.55Accuracy (%)30
MERA - PARus66.2Accuracy (%)28.7

Interactive version: theaggregate.ai/model?slug=yi-coder-9b · How It Works · Data refreshed daily, snapshot 2026-09-05.