Granite 4.0 350M: benchmark results
Provider: IBM. Released 2025-10-01. Access: Open.
Unified ELO 1370 ± 1, rank #1222 of 1392 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 5.51 | Accuracy (%) | 36.4 |
| AA CritPt | 0 | Accuracy (%) | 24.4 |
| AA Omniscience - Software Engineering (SWE) - Go | 8 | Accuracy (%) | 20 |
| CritPt | 0 | Accuracy (self-reported) | 16 |
| AA Omniscience - Software Engineering (SWE) - R | 2 | Accuracy (%) | 14 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 8 | Accuracy (%) | 13.7 |
| AA Omniscience - Software Engineering (SWE) - Swift | 16 | Accuracy (%) | 13.5 |
| AA Omniscience - Software Engineering (SWE) - Julia | 0 | Accuracy (%) | 10.8 |
| AA TAU-2 Bench | 13.16 | Accuracy (%) | 10.6 |
| Artificial Analysis Intelligence Index | 1 | Intelligence Index | 9.4 |
| AA Omniscience | -69.35 | Score | 8 |
| Gorilla API Bench (BFCL) | 18.98 | Overall Accuracy (%) | 7.3 |
Interactive version: theaggregate.ai/model?slug=granite-4-0-350m · How It Works · Data refreshed daily, snapshot 2026-09-05.