Model comparison
Gemma 4 31B IT vs MiniMax-M2
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 37.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MiniMaxSummary
- They share 17 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and MiniMax-M2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 4 31B IT leads 53.8 to 45.3.
- The biggest single-benchmark swing is NYT Connections (extended): 70.6% for Gemma 4 31B IT and 14.8% for MiniMax-M2.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- Gemma 4 31B IT accepts more context: 262K tokens versus 205K.
Side by side
| Gemma 4 31B IT | MiniMax-M2 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 43.5 | 37.4 |
| Released | 2026-04-02 | 2025-10-27 |
| Weights | Open | Open |
| Context window | 262K | 205K |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.09 | $0.30 |
| Output $ / M tokens | $0.34 | $1.20 |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), MiniMax-M2: 39.3 (#159)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1366 | 1297 |
| LMArena Coding | 1459 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), MiniMax-M2: 19.4 (#258)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 57.8% |
| NYT Connections (extended) | 70.6% | 14.8% |
| LMArena Hard Prompts | 1448 | 1357 |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), MiniMax-M2: 37.3 (#160)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1465 | 1352 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Too close to call
Gemma 4 31B IT: 37.9 (#151), MiniMax-M2: 37.0 (#163)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1465 | 1337 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), MiniMax-M2: —
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), MiniMax-M2: 45.3 (#171)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1431 | 1313 |
| LMArena Chinese | 1476 | 1366 |
| LMArena French | 1435 | 1335 |
| LMArena Russian | 1460 | 1331 |
| LMArena Spanish | 1444 | 1326 |
| LMArena German | — | 1355 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), MiniMax-M2: 70.2 (#166)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1328 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), MiniMax-M2: 40.5 (#153)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1446 | 1331 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), MiniMax-M2: 53.0 (#162)
| Benchmark | Gemma 4 31B IT | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1443 | 1340 |
| LMArena Creative Writing | 1415 | 1286 |
| LMArena Multi-Turn | 1452 | 1361 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than MiniMax-M2?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 37.4 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or MiniMax-M2?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is Gemma 4 31B IT or MiniMax-M2 better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 39.3 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 205K.
How many benchmarks do Gemma 4 31B IT and MiniMax-M2 share?
17 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and MiniMax-M2 has 21.