Model comparison
Gemma 3 27B vs MiniMax-M2.7
MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 30.5 on the Noometry Index. Gemma 3 27B costs 5.2× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Google
MiniMaxSummary
- They share 21 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and MiniMax-M2.7 in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.7 leads 41.4 to 22.1.
- The biggest single-benchmark swing is SciCode: 21.2% for Gemma 3 27B and 47% for MiniMax-M2.7.
- Gemma 3 27B is cheaper at $0.08 / $0.16 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 27B | MiniMax-M2.7 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 30.5 | 37.4 |
| Released | 2025-03-11 | 2026-03-18 |
| Weights | Open | Open |
| Context window | 131K | 205K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.08 | $0.30 |
| Output $ / M tokens | $0.16 | $1.20 |
| Results tracked | 43 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
Gemma 3 27B: 22.1 (#329), MiniMax-M2.7: 41.4 (#115)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| SciCode | 21.2% | 47% |
| LMArena Coding | 1322 | 1454 |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1397 |
| WeirdML | — | 37% |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use Too close to call
Gemma 3 27B: 24.9 (#105), MiniMax-M2.7: 24.9 (#103)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| Berkeley Function Calling Leaderboard | 29.5% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning MiniMax-M2.7 leads
Gemma 3 27B: 16.3 (#297), MiniMax-M2.7: 19.0 (#248)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1340 | 1422 |
| Epoch Capabilities Index | 130.04 | 145.84 |
| Kagi LLM Benchmark | 40.4% | — |
| NYT Connections (extended) | — | 24.7% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 39.3% |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| LiveBench | 50% | — |
Math Too close to call
Gemma 3 27B: 24.4 (#261), MiniMax-M2.7: 24.9 (#254)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1312 | 1420 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| ProofBench | — | 3% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge MiniMax-M2.7 leads
Gemma 3 27B: 25.4 (#256), MiniMax-M2.7: 37.1 (#151)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 12.9% |
| LMArena Expert | 1303 | 1443 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
Multimodal Not comparable
Gemma 3 27B: 32.0 (#94), MiniMax-M2.7: —
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |
Multilingual MiniMax-M2.7 leads
Gemma 3 27B: 47.0 (#150), MiniMax-M2.7: 50.5 (#120)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1334 | 1382 |
| LMArena Chinese | 1347 | 1439 |
| LMArena French | 1368 | 1422 |
| LMArena German | 1362 | 1398 |
| LMArena Japanese | 1287 | 1261 |
| LMArena Korean | 1308 | 1313 |
| LMArena Russian | 1349 | 1383 |
| LMArena Spanish | 1348 | 1403 |
Instruction Following MiniMax-M2.7 leads
Gemma 3 27B: 70.8 (#155), MiniMax-M2.7: 74.2 (#101)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1404 |
| LiveBench Instruction Following | 74.9% | — |
Long Context MiniMax-M2.7 leads
Gemma 3 27B: 27.6 (#288), MiniMax-M2.7: 43.3 (#94)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1333 | 1419 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference MiniMax-M2.7 leads
Gemma 3 27B: 52.7 (#161), MiniMax-M2.7: 59.1 (#107)
| Benchmark | Gemma 3 27B | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1358 | 1404 |
| LMArena Creative Writing | 1346 | 1354 |
| LMArena Multi-Turn | 1344 | 1413 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than MiniMax-M2.7?
MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 30.5 on the Noometry Index. Gemma 3 27B costs 5.2× 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 27B or MiniMax-M2.7?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.
Is Gemma 3 27B or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 22.1 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 27B and MiniMax-M2.7 share?
21 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and MiniMax-M2.7 has 30.