Gemma 2 9B benchmark results
7 results on 7 benchmarks from 4 sources.
Open weights Released: Jun 24, 2024 Updated Oct 22, 2026
Also listed as: gemma-2-9b-it · Gemma 2 Instruct (9B) · Gemma-2-9B · Gemma-2-9B-it · google/gemma-2-9b-it · google/gemma-2-9b
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1267 | 311 | Overall, style control on; 54611 votes; 95% CI 1263–1271“gemma-2-9b-it” | Official leaderboard | Oct 8, 2026 |
| Open LLM Leaderboard v2 | 32.1% | 843 | Average of 6 normalised benchmarks; bfloat16; 9B params“google/gemma-2-9b-it” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 27.5% | 267 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| MMLU | 72.1% | 49 | Exact match; 5-shot | Official leaderboard via Epoch AI | Jun 24, 2024 |
| MMLU-Pro | 45.1% | 175 | Overall accuracy; data source: TIGER-Lab; 9B“Gemma-2-9B” | Official leaderboard | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 0.6% | 260 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Mar 7, 2025 |
| MATH Level 5 | 21.0% | 87 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
FAQ
Where do these Gemma 2 9B scores come from?
From Epoch AI Benchmarking Hub, 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.