Model comparison
Gemma 2 27B vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Google
MiniMaxSummary
- They share 15 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and MiniMax-M2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2 leads 37.3 to 10.7.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- MiniMax-M2 accepts more context: 205K tokens versus 8K.
Side by side
| Gemma 2 27B | MiniMax-M2 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 29.4 | 37.4 |
| Released | 2024-06-24 | 2025-10-27 |
| Weights | Open | Open |
| Context window | 8K | 205K |
| Max output | 2K | 131K |
| Input $ / M tokens | $0.65 | $0.30 |
| Output $ / M tokens | $0.65 | $1.20 |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Gemma 2 27B: 34.1 (#246), MiniMax-M2: 39.3 (#159)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1211 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
Gemma 2 27B: 15.3 (#315), MiniMax-M2: 19.4 (#258)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |
Math MiniMax-M2 leads
Gemma 2 27B: 10.7 (#311), MiniMax-M2: 37.3 (#160)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1212 | 1352 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge MiniMax-M2 leads
Gemma 2 27B: 19.0 (#280), MiniMax-M2: 37.0 (#163)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1172 | 1337 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |
Multilingual MiniMax-M2 leads
Gemma 2 27B: 38.6 (#226), MiniMax-M2: 45.3 (#171)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1217 | 1313 |
| LMArena Chinese | 1221 | 1366 |
| LMArena French | 1247 | 1335 |
| LMArena German | 1209 | 1355 |
| LMArena Russian | 1234 | 1331 |
| LMArena Spanish | 1228 | 1326 |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |
Instruction Following MiniMax-M2 leads
Gemma 2 27B: 60.5 (#249), MiniMax-M2: 70.2 (#166)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1206 | 1328 |
| LiveBench Instruction Following | 58.1% | — |
Long Context MiniMax-M2 leads
Gemma 2 27B: 37.3 (#218), MiniMax-M2: 40.5 (#153)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1231 | 1331 |
Writing & Preference MiniMax-M2 leads
Gemma 2 27B: 44.2 (#225), MiniMax-M2: 53.0 (#162)
| Benchmark | Gemma 2 27B | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1231 | 1340 |
| LMArena Creative Writing | 1241 | 1286 |
| LMArena Multi-Turn | 1224 | 1361 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B or MiniMax-M2?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 8K.
How many benchmarks do Gemma 2 27B and MiniMax-M2 share?
15 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and MiniMax-M2 has 21.