Google DeepMind·released 2025-03-121 source
Gemma 3 12B benchmark scores: 5 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 19.28 on GPQA diamond (unverified)·0 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| GPQA diamond | 19.28accuracy (%) | unverifiedT2 | 2025-03-12 |
| OTIS Mock AIME 2024-2025 | 16.58accuracy (%) | unverifiedT2 | 2025-03-12 |
| DTBench | 14.67accuracy (%) | unverifiedT1 | 2025-03-12https://conceptualreasoning.ai/dtbench |
| LMCA | 5.25accuracy (%) | unverifiedT1 | 2025-03-12https://conceptualreasoning.ai/lmca |
| Chess Puzzles | 0accuracy (%) | unverifiedT2 | 2025-03-12 |
Claims drawn from cited facts, not live model generation.
This model was developed by Google DeepMind and released in 2025.
2 cited facts
The model is scored on five tracked benchmarks and currently holds no top score. Its record is unverified, meaning neither confirmed nor disputed by outside evaluation.
3 cited facts
On average, this model trails the state-of-the-art leader by 76.18 points on its benchmarks, a gap that under the disclosed harness reads as well behind the front of the pack rather than at the frontier. It holds the top score on none of those benchmarks, meaning it has no category leadership at this time.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Gemma 3 12B is an AI model developed by Google DeepMind, released 2025-03-12. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Gemma 3 12B has recorded scores on 5 benchmarks, each shown with its evidence status.
Gemma 3 12B has recorded scores on 5 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, DTBench, LMCA, Chess Puzzles. The full table above shows each score with its evidence status.
0 of 5 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Gemma 3 12B has 5 tracked claims: 5 unverified.