starcoderbase: benchmark results

Provider: BigCode. Access: Open.

Unified ELO 1277 ± 21, rank #2764 of 2928 rated models, from 19 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ToolBench - WebShop Long5.8Task Score100
EffiBench - NMU1.87Normalized Memory Usage92.7
EffiBench - NET2.8Normalized Execution Time90.2
ToolBench - WebShop Short23.1Task Score86
SAFIM55.54Average85.7
ToolBench Leaderboard52.21Average Task Score74.4
ToolBench - Google Sheets42.9Task Score72.1
ToolBench - The Cat API86Task Score68.6
ToolBench - Open Weather90Task Score67.4
ToolBench - Trip Booking63.3Task Score65.1
ToolBench - Tabletop17.1Task Score64
ToolBench - Home Search79Task Score62.8

Interactive version: theaggregate.ai/model?slug=starcoderbase · How It Works · Data refreshed daily, snapshot 2026-09-23.