starcoder2-7B — benchmark results

Provider: BigCode. Released 2024-02-28. Access: Open.

Unified ELO 1205 ± 20, rank #1687 of 1776 rated models, from 29 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EvoEval Tool Use46Pass@1 (%)43
EffiBench - NET3.02Normalized Execution Time42.7
ShaderMatch10.15Clone Match Rate (%)38.1
BigCode Models Leaderboard34.1HumanEval Python Pass@1 (%)35.6
GSM8K32.7Accuracy (%)33
CRUXEval36Output Prediction pass@1 (%)32.1
Open LLM Leaderboard - MuSR5.82Score28.2
EvoEval Creative17Pass@1 (%)24
Big Code Memorization - HumanEval pass@136.59HumanEval pass@1 (%)23.5
Big Code Memorization - HumanEval pass@5029.05HumanEval pass@50 (%)23.5
Big Code Memorization - HumanEval-ET pass@132.32HumanEval-ET pass@1 (%)23.5
EvoEval Subtle38Pass@1 (%)23

Interactive version: theaggregate.ai/model?slug=starcoder2-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.