Model comparison
Gemma 3n E4b IT vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
MiniMaxSummary
- They share 18 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 3 categories and MiniMax-M2.5 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 37.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 31.5% for Gemma 3n E4b IT and 55.2% for MiniMax-M2.5.
Side by side
| Gemma 3n E4b IT | MiniMax-M2.5 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 37.3 | 38.3 |
| Released | — | 2026-02-12 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 18 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Gemma 3n E4b IT: 37.0 (#198), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1268 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, MiniMax-M2.5: 30.4 (#77)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.9 (#247), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 55.2% |
| LMArena Hard Prompts | 1284 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| Epoch Capabilities Index | — | 146.68 |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 35.1 (#188), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1251 | 1378 |
| ProofBench | — | 4% |
Knowledge MiniMax-M2.5 leads
Gemma 3n E4b IT: 34.2 (#198), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1246 | 1379 |
| Vectara Hallucination Rate | — | 9.1% |
Multilingual MiniMax-M2.5 leads
Gemma 3n E4b IT: 43.4 (#183), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1285 | 1338 |
| LMArena Chinese | 1309 | 1393 |
| LMArena French | 1330 | 1362 |
| LMArena German | 1311 | 1362 |
| LMArena Japanese | 1272 | 1171 |
| LMArena Korean | 1259 | 1232 |
| LMArena Russian | 1288 | 1358 |
| LMArena Spanish | 1305 | 1354 |
Instruction Following MiniMax-M2.5 leads
Gemma 3n E4b IT: 66.1 (#210), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1255 | 1353 |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.7 (#191), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1276 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Gemma 3n E4b IT: 50.1 (#186), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Gemma 3n E4b IT | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1306 | 1359 |
| LMArena Creative Writing | 1287 | 1331 |
| LMArena Multi-Turn | 1276 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
Frequently asked questions
Is Gemma 3n E4b IT better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.3 on the Noometry Index.
Is Gemma 3n E4b IT or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 37.0 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and MiniMax-M2.5 share?
18 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and MiniMax-M2.5 has 33.