Gemma 7B benchmark results
6 results on 4 benchmarks from 4 sources.
Open weights Released: Feb 21, 2024 Updated Oct 22, 2026
Also listed as: gemma-7b · Gemma (7B) · Gemma 7b · Gemma-7B · google/gemma-7b
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| Open LLM Leaderboard v2 | 15.4% | 3260 | Average of 6 normalised benchmarks; bfloat16; 8.538B params“google/gemma-7b” | Official leaderboard | Mar 13, 2025 |
| MMLU | 64.3% | 40 | Exact match; 5-shot | Paper / tech report via Epoch AI | Feb 21, 2024 |
| MMLU | 66.1% | 65 | Exact match; 5-shot | Official leaderboard via Epoch AI | Feb 21, 2024 |
| MMLU-Pro | 33.7% | 209 | Overall accuracy; data source: TIGER-Lab; 7B“Gemma-7B” | Official leaderboard | Mar 11, 2026 |
| HumanEval / HumanEval+ | 35.4% | 85 | HumanEval (base tests), pass@1 greedy“gemma-7b” | Official leaderboard | Dec 26, 2024 |
| HumanEval / HumanEval+ | 28.7% | 89 | HumanEval+ (extended tests), pass@1 greedy“gemma-7b” | Official leaderboard | Dec 26, 2024 |
FAQ
Where do these Gemma 7B scores come from?
From EvalPlus leaderboard, Epoch AI Benchmarking Hub, 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.