deepseek-coder-1.3B-instruct — benchmark results

Provider: DeepSeek. Released 2023-10-29. Access: Open.

Unified ELO 1243 ± 34, rank #1631 of 1776 rated models, from 23 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EffiBench - NET2.82Normalized Execution Time85.4
EvoEval Concise60.98Pass@1 (%)62
InfiBench41.32Score (%)61.9
EvoEval Subtle53Pass@1 (%)59
EffiBench - NMU1.91Normalized Memory Usage58.5
EvalPlus (HumanEval+ & MBPP+)57.6Pass@1 avg (%)54
EvoEval40.96Pass@1 (%)54
EvoEval Verbose57.32Pass@1 (%)53
EvoEval Creative25Pass@1 (%)51
EvoEval Combine9Pass@1 (%)44
EvoEval Difficult20Pass@1 (%)41
EvoEval Tool Use39Pass@1 (%)19

Interactive version: theaggregate.ai/model?slug=deepseek-coder-1-3b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.