Model comparison
Gemma 3 4B vs MiniMax-M2.7
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 28.1 on the Noometry Index. Gemma 3 4B costs 10× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Google
MiniMaxSummary
- They share 14 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and MiniMax-M2.7 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.7 to 11.8.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 6.4% for Gemma 3 4B and 12.9% for MiniMax-M2.7.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- MiniMax-M2.7 accepts more context: 205K tokens versus 131K.
Side by side
| Gemma 3 4B | MiniMax-M2.7 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 28.1 | 37.7 |
| Released | 2025-03-12 | 2026-03-18 |
| Weights | Open | Open |
| Context window | 131K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.04 | $0.30 |
| Output $ / M tokens | $0.08 | $1.20 |
| Results tracked | 22 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
Gemma 3 4B: 35.9 (#215), MiniMax-M2.7: 41.8 (#120)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1230 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use MiniMax-M2.7 leads
Gemma 3 4B: 20.9 (#142), MiniMax-M2.7: 25.1 (#111)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| Berkeley Function Calling Leaderboard | 19.6% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning MiniMax-M2.7 leads
Gemma 3 4B: 13.2 (#335), MiniMax-M2.7: 19.7 (#253)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1422 |
| Epoch Capabilities Index | 116.02 | 145.85 |
| Kagi LLM Benchmark | 25.2% | — |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 39.3% |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
Math MiniMax-M2.7 leads
Gemma 3 4B: 16.8 (#292), MiniMax-M2.7: 25.9 (#263)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1239 | 1420 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| ProofBench | — | 3% |
Knowledge MiniMax-M2.7 leads
Gemma 3 4B: 11.8 (#299), MiniMax-M2.7: 37.7 (#152)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 6.4% | 12.9% |
| LMArena Expert | 1223 | 1444 |
| GPQA Diamond | 23.2% | — |
Multilingual MiniMax-M2.7 leads
Gemma 3 4B: 42.5 (#194), MiniMax-M2.7: 50.3 (#123)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1273 | 1382 |
| LMArena German | 1281 | 1398 |
| LMArena Russian | 1294 | 1383 |
| LMArena Chinese | — | 1441 |
| LMArena French | — | 1421 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1313 |
| LMArena Spanish | — | 1403 |
Instruction Following MiniMax-M2.7 leads
Gemma 3 4B: 65.2 (#225), MiniMax-M2.7: 74.1 (#103)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1405 |
Long Context MiniMax-M2.7 leads
Gemma 3 4B: 38.7 (#194), MiniMax-M2.7: 43.3 (#99)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1273 | 1419 |
Writing & Preference MiniMax-M2.7 leads
Gemma 3 4B: 42.0 (#239), MiniMax-M2.7: 58.9 (#112)
| Benchmark | Gemma 3 4B | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1291 | 1405 |
| LMArena Creative Writing | 1271 | 1354 |
| LMArena Multi-Turn | 1255 | 1412 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than MiniMax-M2.7?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 28.1 on the Noometry Index. Gemma 3 4B costs 10× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or MiniMax-M2.7?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.
Is Gemma 3 4B or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.7 does, with 205K tokens against 131K.
How many benchmarks do Gemma 3 4B and MiniMax-M2.7 share?
14 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and MiniMax-M2.7 has 30.