Model comparison
Gemma 2 27B vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 29.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
MiniMaxSummary
- They share 18 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and MiniMax-M2.5 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.5 leads 38.6 to 18.9.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- MiniMax-M2.5 accepts more context: 205K tokens versus 8K.
Side by side
| Gemma 2 27B | MiniMax-M2.5 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 29.2 | 38.1 |
| Released | 2024-06-24 | 2026-02-12 |
| 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 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Gemma 2 27B: 33.5 (#243), MiniMax-M2.5: 47.9 (#53)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1211 | 1380 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1386 |
| SWE-bench Multilingual | — | 68.3% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, MiniMax-M2.5: 30.2 (#70)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning MiniMax-M2.5 leads
Gemma 2 27B: 14.8 (#313), MiniMax-M2.5: 17.6 (#281)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1199 | 1372 |
| Epoch Capabilities Index | 122.06 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| LiveBench | 38.2% | — |
Math MiniMax-M2.5 leads
Gemma 2 27B: 10.0 (#306), MiniMax-M2.5: 25.8 (#242)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1212 | 1378 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| ProofBench | — | 4% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge MiniMax-M2.5 leads
Gemma 2 27B: 18.9 (#275), MiniMax-M2.5: 38.6 (#132)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1172 | 1378 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 9.1% |
| MMLU | 75.7% | — |
Multilingual MiniMax-M2.5 leads
Gemma 2 27B: 38.8 (#221), MiniMax-M2.5: 47.3 (#147)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1217 | 1338 |
| LMArena Chinese | 1221 | 1392 |
| LMArena French | 1246 | 1363 |
| LMArena German | 1209 | 1361 |
| LMArena Japanese | 1175 | 1169 |
| LMArena Korean | 1174 | 1232 |
| LMArena Russian | 1234 | 1359 |
| LMArena Spanish | 1228 | 1354 |
Instruction Following MiniMax-M2.5 leads
Gemma 2 27B: 60.7 (#244), MiniMax-M2.5: 71.7 (#143)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1206 | 1353 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Too close to call
Gemma 2 27B: 37.3 (#213), MiniMax-M2.5: 37.4 (#211)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1231 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Gemma 2 27B: 44.4 (#220), MiniMax-M2.5: 54.1 (#149)
| Benchmark | Gemma 2 27B | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1231 | 1359 |
| LMArena Creative Writing | 1241 | 1331 |
| LMArena Multi-Turn | 1224 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 29.2 on the Noometry Index.
Which is cheaper, Gemma 2 27B or MiniMax-M2.5?
MiniMax-M2.5 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-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.5 does, with 205K tokens against 8K.
How many benchmarks do Gemma 2 27B and MiniMax-M2.5 share?
18 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and MiniMax-M2.5 has 33.