granite-3.2-2B-instruct: benchmark results
IBM's Apache-2.0 2B Granite 3.2 instruct model (February 2025) with an experimental chain-of-thought reasoning mode that can be toggled on or off. Provider: IBM. Released 2025-02-26. Access: Open.
Aggregate Rating 1375 ± 46, rank #7025 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Toxicity Risk | 0.18 | Risk Score | 94.7 |
| Open LLM Leaderboard - IFEval | 61.52 | Score | 73.7 |
| Enkrypt AI - Safety Risk | 23.6 | Risk Score | 66.2 |
| Open LLM Leaderboard - MATH Level 5 | 14.43 | Score | 60.7 |
| Enkrypt AI - Jailbreak Risk | 7.76 | Risk Score | 60.5 |
| Open LLM Leaderboard - GPQA | 29.03 | Score | 45 |
| Open LLM Leaderboard - BBH | 43.87 | Score | 31.2 |
| Enkrypt AI - Bias Risk | 86.82 | Risk Score | 30.6 |
| Open LLM Leaderboard - MMLU-Pro | 27.83 | Score | 30.5 |
| Enkrypt AI - Risk Score | 38.77 | Risk Score | 27.7 |
| Enkrypt AI - Insecure Code Risk | 49.33 | Risk Score | 23.8 |
| Open LLM Leaderboard - MuSR | 36.46 | Score | 20.4 |
Interactive version: theaggregate.ai/model?slug=granite-3-2-2b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.