OpenCoder-8B-Instruct — benchmark results

Provider: Other. Released 2024-11-07. Access: Open.

Unified ELO 1355 ± 28, rank #1396 of 1776 rated models, from 18 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EvalPlus (HumanEval+ & MBPP+)74.4Pass@1 avg (%)88.7
BigCodeBench43.2Pass@1 (%)69
EvalPlus74.4EvalPlus Avg. (self-reported)50
MBPP+71.4MBPP+ pass@1 (self-reported)50
EuroEval Portuguese NLU - ScaLA PT7.5Linguistic acceptability Score (%)40
FullStackBench en43.63Score (self-reported)37
HumanEval+77.4HumanEval+ pass@1 (self-reported)37
EuroEval Italian NLU - ScaLA IT9.48Linguistic acceptability Score (%)35.6
EuroEval Italian NLU - Sentipolc1642.93Sentiment classification Score (%)35.3
EuroEval Portuguese NLU - SST-2 PT67.12Sentiment classification Score (%)32
EuroEval Dutch NLU - DBRD69.4Sentiment classification Score (%)27.2
EuroEval Norwegian Common Sense Reasoning14.03Common Sense Reasoning Average Score (%)27.1

Interactive version: theaggregate.ai/model?slug=opencoder-8b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.