Granite 3.3 8B Base: benchmark results
Provider: IBM. Released 2025-04-16.
Aggregate Rating 1393 ± 40, rank #6428 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ShatterMed-QA (Chinese, Easy) | 96.39 | Accuracy (%) on the 2,616 Chinese Easy multiple-choice clini | 70 |
| LLM Stats (TriviaQA) | 78.18 | Score (%) | 68.8 |
| LLM Stats (AIME 2024) | 81.2 | Score (%) | 54.5 |
| ShatterMed-QA (Chinese, Hard) | 70.95 | Accuracy (%) on the 327 Chinese Hard multiple-choice clinica | 20 |
| ShatterMed-QA (English, Hard) | 65.27 | Accuracy (%) on the 1,692 English Hard multiple-choice clini | 20 |
| LLM Stats Score | -1.06 | LLM Stats Score (conservative rating) | 10 |
| ShatterMed-QA (English, Easy) | 68.12 | Accuracy (%) on the 5,923 English Easy multiple-choice clini | 5 |
| LLM Stats (DROP) | 36.14 | Score (%) | 3.6 |
| ZeroEval MATH-500 | 69.02 | MATH-500 Score | 1.6 |
Interactive version: theaggregate.ai/model?slug=granite-3-3-8b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.