Gemma 3 1B benchmark results
4 results on 4 benchmarks from 3 sources.
Open weights Released: Mar 12, 2025 Updated Oct 22, 2026
Also listed as: gemma-3-1b-it · Gemma-3-1b-it (Prompt) · Gemma-3-1B-it
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 19.9% | 278 | Epoch AI run, accuracy | Independent run | Aug 28, 2026 |
| MMLU-Pro | 14.7% | 239 | Overall accuracy; data source: Self-Reported; 1B“Gemma-3-1B-it” | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 1.1% | 255 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 28, 2026 |
| BFCL v4 (function calling) | 7.2% | 109 | Overall accuracy; prompt-based“Gemma-3-1b-it (Prompt)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these Gemma 3 1B scores come from?
From Epoch AI Benchmarking Hub, Berkeley Function Calling Leaderboard (BFCL), and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.