Model comparison
Gemma 3 27B vs MiniMax M1
MiniMax M1 is the stronger model overall, scoring 40.3 to 30.8 on the Noometry Index. Gemma 3 27B costs 9.6× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Google
MiniMaxSummary
- They share 18 benchmarks with published results for both. Gemma 3 27B scores higher in 2 categories and MiniMax M1 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax M1 leads 39.9 to 22.5.
- The biggest single-benchmark swing is Fiction.LiveBench: 33.3% for Gemma 3 27B and 69.4% for MiniMax M1.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.55 / $2.20 for MiniMax M1.
- MiniMax M1 accepts more context: 1M tokens versus 131K.
Side by side
| Gemma 3 27B | MiniMax M1 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 30.8 | 40.3 |
| Released | 2025-03-11 | 2025-06-13 |
| Weights | Open | Open |
| Context window | 131K | 1M |
| Max output | 8K | 40K |
| Input $ / M tokens | $0.08 | $0.55 |
| Output $ / M tokens | $0.16 | $2.20 |
| Results tracked | 43 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
Gemma 3 27B: 22.5 (#334), MiniMax M1: 39.9 (#153)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1322 | 1359 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), MiniMax M1: —
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning MiniMax M1 leads
Gemma 3 27B: 16.7 (#301), MiniMax M1: 26.9 (#126)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1339 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math MiniMax M1 leads
Gemma 3 27B: 25.9 (#265), MiniMax M1: 37.5 (#151)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Math | 1312 | 1361 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge MiniMax M1 leads
Gemma 3 27B: 25.5 (#261), MiniMax M1: 36.4 (#170)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1304 | 1317 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), MiniMax M1: —
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), MiniMax M1: 45.8 (#163)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1334 | 1319 |
| LMArena Chinese | 1346 | 1360 |
| LMArena French | 1368 | 1370 |
| LMArena German | 1362 | 1350 |
| LMArena Japanese | 1287 | 1217 |
| LMArena Korean | 1308 | 1266 |
| LMArena Russian | 1349 | 1329 |
| LMArena Spanish | 1349 | 1353 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), MiniMax M1: 69.3 (#174)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1312 |
| LiveBench Instruction Following | 74.9% | — |
Long Context MiniMax M1 leads
Gemma 3 27B: 27.6 (#293), MiniMax M1: 41.4 (#141)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| Fiction.LiveBench | 33.3% | 69.4% |
| LMArena Longer Query | 1333 | 1326 |
Writing & Preference Too close to call
Gemma 3 27B: 52.5 (#168), MiniMax M1: 53.1 (#161)
| Benchmark | Gemma 3 27B | MiniMax M1 |
|---|---|---|
| LMArena Text | 1358 | 1343 |
| LMArena Creative Writing | 1346 | 1298 |
| LMArena Multi-Turn | 1345 | 1335 |
| 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 M1?
MiniMax M1 is the stronger model overall, scoring 40.3 to 30.8 on the Noometry Index. Gemma 3 27B costs 9.6× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or MiniMax M1?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; MiniMax M1 lists at $0.55 and $2.20.
Is Gemma 3 27B or MiniMax M1 better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.9 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax M1 does, with 1M tokens against 131K.
How many benchmarks do Gemma 3 27B and MiniMax M1 share?
18 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and MiniMax M1 has 18.