starcoderbase: benchmark results
Provider: BigCode. Access: Open.
Unified ELO 1277 ± 21, rank #2764 of 2928 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ToolBench - WebShop Long | 5.8 | Task Score | 100 |
| EffiBench - NMU | 1.87 | Normalized Memory Usage | 92.7 |
| EffiBench - NET | 2.8 | Normalized Execution Time | 90.2 |
| ToolBench - WebShop Short | 23.1 | Task Score | 86 |
| SAFIM | 55.54 | Average | 85.7 |
| ToolBench Leaderboard | 52.21 | Average Task Score | 74.4 |
| ToolBench - Google Sheets | 42.9 | Task Score | 72.1 |
| ToolBench - The Cat API | 86 | Task Score | 68.6 |
| ToolBench - Open Weather | 90 | Task Score | 67.4 |
| ToolBench - Trip Booking | 63.3 | Task Score | 65.1 |
| ToolBench - Tabletop | 17.1 | Task Score | 64 |
| ToolBench - Home Search | 79 | Task Score | 62.8 |
Interactive version: theaggregate.ai/model?slug=starcoderbase · How It Works · Data refreshed daily, snapshot 2026-09-23.