Model comparison
Gemma 2B vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
Google
MiniMaxSummary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and MiniMax-M2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2 leads 53.0 to 24.0.
Side by side
| Gemma 2B | MiniMax-M2 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 29.6 | 37.4 |
| Released | 2024-02-21 | 2025-10-27 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 23 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Gemma 2B: 29.4 (#305), MiniMax-M2: 39.3 (#159)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1010 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Too close to call
Gemma 2B: 18.8 (#275), MiniMax-M2: 19.4 (#258)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 989 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math MiniMax-M2 leads
Gemma 2B: 30.0 (#239), MiniMax-M2: 37.3 (#160)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1009 | 1352 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, MiniMax-M2: 37.0 (#163)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Expert | — | 1337 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual MiniMax-M2 leads
Gemma 2B: 23.0 (#294), MiniMax-M2: 45.3 (#171)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 958 | 1313 |
| LMArena Chinese | 986 | 1366 |
| LMArena Russian | 937 | 1331 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Spanish | — | 1326 |
Instruction Following MiniMax-M2 leads
Gemma 2B: 48.5 (#302), MiniMax-M2: 70.2 (#166)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 970 | 1328 |
Long Context MiniMax-M2 leads
Gemma 2B: 29.9 (#291), MiniMax-M2: 40.5 (#153)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 981 | 1331 |
Writing & Preference MiniMax-M2 leads
Gemma 2B: 24.0 (#308), MiniMax-M2: 53.0 (#162)
| Benchmark | Gemma 2B | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1002 | 1340 |
| LMArena Creative Writing | 987 | 1286 |
| LMArena Multi-Turn | 945 | 1361 |
Frequently asked questions
Is Gemma 2B better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.6 on the Noometry Index.
Is Gemma 2B or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and MiniMax-M2 share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and MiniMax-M2 has 21.