IBM
Granite-3.1-8B-Instruct benchmark results
4 results on 4 benchmarks from 4 sources.
Open weights Updated Oct 22, 2026
Also listed as: granite-3.1-8b-instruct · Granite-3.1-8B-Instruct (FC) · ibm-granite/granite-3.1-8b-instruct
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1209 | 342 | Overall, style control on; 3090 votes; 95% CI 1197–1220“granite-3.1-8b-instruct” | Official leaderboard | Oct 8, 2026 |
| Open LLM Leaderboard v2 | 30.6% | 945 | Average of 6 normalised benchmarks; float16; 8.171B params“ibm-granite/granite-3.1-8b-instruct” | Official leaderboard | Mar 13, 2025 |
| MMLU-Pro | 41.0% | 189 | Overall accuracy; data source: TIGER-Lab; 8B | Official leaderboard | Mar 11, 2026 |
| BFCL v4 (function calling) | 27.1% | 81 | Overall accuracy; native function calling (FC)“Granite-3.1-8B-Instruct (FC)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these Granite-3.1-8B-Instruct scores come from?
From Berkeley Function Calling Leaderboard (BFCL), LMArena leaderboard dataset, MMLU-Pro leaderboard (TIGER-Lab), and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.