granite-3.2-8B-instruct: benchmark results
IBM's Granite 3.2 8B instruct model with an experimental toggleable thinking mode for step-by-step reasoning. Provider: IBM. Released 2025-02-26. Access: Open.
Aggregate Rating 1449 ± 36, rank #3799 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Toxicity Risk | 0.45 | Risk Score | 90.8 |
| Open LLM Leaderboard - IFEval | 72.75 | Score | 86.8 |
| Open LLM Leaderboard - MuSR | 45.62 | Score | 86.3 |
| Open LLM Leaderboard - MATH Level 5 | 23.79 | Score | 77.2 |
| Open LLM Leaderboard - GPQA | 31.54 | Score | 71.9 |
| Open LLM Leaderboard - BBH | 54.02 | Score | 69 |
| Enkrypt AI - Jailbreak Risk | 7.63 | Risk Score | 61.4 |
| Enkrypt AI - Safety Risk | 24.23 | Risk Score | 61.4 |
| Open LLM Leaderboard - MMLU-Pro | 35.12 | Score | 51.8 |
| Enkrypt AI - Insecure Code Risk | 49.33 | Risk Score | 23.8 |
| Enkrypt AI - Risk Score | 39.74 | Risk Score | 22.8 |
| Enkrypt AI - Bias Risk | 87.6 | Risk Score | 22.5 |
Interactive version: theaggregate.ai/model?slug=granite-3-2-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.