Google DeepMind·released 2025-03-121 source
Gemma 3 4B 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 18.22 on DTBench (unverified)·0 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| DTBench | 18.22accuracy (%) | unverifiedT1 | 2025-03-12https://conceptualreasoning.ai/dtbench |
| OTIS Mock AIME 2024-2025 | 7.41accuracy (%) | unverifiedT2 | 2025-03-12 |
| LMCA | 3.27accuracy (%) | unverifiedT1 | 2025-03-12https://conceptualreasoning.ai/lmca |
| GPQA diamond | 0accuracy (%) | unverifiedT2 | 2025-03-12 |
| Chess Puzzles | 0accuracy (%) | unverifiedT2 | 2025-03-12 |
Claims drawn from cited facts, not live model generation.
This model comes from Google DeepMind, placing its origin within a major industrial research lab, and it dates to 2025.
2 cited facts
This model is scored on 5 tracked benchmarks and currently holds no top score. Its record is unverified, meaning outside evaluation has neither confirmed nor disputed the reported numbers.
3 cited facts
On average this model trails the state-of-the-art leader by 81.56 points, a wide gap under a disclosed harness that reads as well behind the front of the pack rather than as a near-frontier result. Consistent with that, it holds the top score on none of its benchmarks, so it shows no category leadership yet.
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 4B 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 4B has recorded scores on 5 benchmarks, each shown with its evidence status.
Gemma 3 4B 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 4B has 5 tracked claims: 5 unverified.