Model comparison
Gemma 3 4B vs Laguna M.1
Laguna M.1 is the stronger model overall, scoring 32.5 to 28.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
PoolsideSummary
- The widest gap is in reasoning, where Laguna M.1 leads 23.1 to 13.2.
- Laguna M.1 accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 4B | Laguna M.1 | |
|---|---|---|
| Provider | Poolside | |
| Noometry Index | 28.1 | 32.5 |
| Released | 2025-03-12 | 2026-04-28 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 4K | 33K |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 3 4B: 35.9 (#215), Laguna M.1: 36.6 (#204)
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| LMArena WebDev | — | 1349 |
| LMArena Coding | 1230 | — |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Laguna M.1: —
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Laguna M.1 leads
Gemma 3 4B: 13.2 (#335), Laguna M.1: 23.1 (#184)
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 116.02 | — |
Math Laguna M.1 leads
Gemma 3 4B: 16.8 (#292), Laguna M.1: 21.1 (#283)
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| ProofBench | — | 0% |
| LMArena Math | 1239 | — |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#299), Laguna M.1: —
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
Multilingual Not comparable
Gemma 3 4B: 42.5 (#194), Laguna M.1: —
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Not comparable
Gemma 3 4B: 65.2 (#225), Laguna M.1: —
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| LMArena Instruction Following | 1239 | — |
Long Context Not comparable
Gemma 3 4B: 38.7 (#194), Laguna M.1: —
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| LMArena Longer Query | 1273 | — |
Writing & Preference Not comparable
Gemma 3 4B: 42.0 (#239), Laguna M.1: —
| Benchmark | Gemma 3 4B | Laguna M.1 |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1271 | — |
| EQ-Bench Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1255 | — |
Frequently asked questions
Is Gemma 3 4B better than Laguna M.1?
Laguna M.1 is the stronger model overall, scoring 32.5 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Laguna M.1 better for coding?
They score almost the same on coding (35.9 vs 36.6); test both on your own repository before choosing.
Which has the bigger context window?
Laguna M.1 does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 4B and Laguna M.1 share?
0 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Laguna M.1 has 3.