Model comparison
Gemma 4 26B A4B IT vs MiniMax-M2.1
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 38.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MiniMaxSummary
- They share 17 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 7 categories and MiniMax-M2.1 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 45.7 to 35.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.2% for Gemma 4 26B A4B IT and 11.8% for MiniMax-M2.1.
- Gemma 4 26B A4B IT is cheaper at $0.0765 / $0.26 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- Gemma 4 26B A4B IT accepts more context: 262K tokens versus 205K.
Side by side
| Gemma 4 26B A4B IT | MiniMax-M2.1 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 43.1 | 38.4 |
| Released | 2026-04-02 | 2025-12-23 |
| Weights | Open | Open |
| Context window | 262K | 205K |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.0765 | $0.30 |
| Output $ / M tokens | $0.26 | $1.20 |
| Results tracked | 28 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Gemma 4 26B A4B IT: 38.8 (#156), MiniMax-M2.1: 40.1 (#132)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | 1359 | 1384 |
| LMArena Coding | 1446 | 1421 |
| ALE-Bench | 927.17 | 623.83 |
| SciCode | 40% | — |
| WeirdML | 35.2% | — |
Agentic & Tool Use Not comparable
Gemma 4 26B A4B IT: —, MiniMax-M2.1: 27.7 (#91)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 21.1 (#205), MiniMax-M2.1: 15.8 (#301)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1438 | 1410 |
| NYT Connections (extended) | — | 11.2% |
| CritPt | 0% | — |
| Chess Puzzles | 6% | — |
| DTBench | 74.9% | — |
| LMCA | 29.7% | — |
| Epoch Capabilities Index | 141.85 | — |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#61), MiniMax-M2.1: 35.6 (#142)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1469 | 1396 |
| OTIS Mock AIME 2024-2025 | 82.2% | — |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.6 (#79), MiniMax-M2.1: 37.7 (#143)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 5.2% | 11.8% |
| LMArena Expert | 1447 | 1432 |
| GPQA Diamond | 73.2% | — |
Multimodal Not comparable
Gemma 4 26B A4B IT: 39.9 (#43), MiniMax-M2.1: —
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.3 (#68), MiniMax-M2.1: 50.2 (#123)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1422 | 1378 |
| LMArena Chinese | 1495 | 1430 |
| LMArena French | 1459 | 1405 |
| LMArena Russian | 1434 | 1386 |
| LMArena Spanish | 1415 | 1396 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1297 |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 75.0 (#78), MiniMax-M2.1: 74.0 (#108)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1399 |
Long Context Too close to call
Gemma 4 26B A4B IT: 43.6 (#87), MiniMax-M2.1: 43.2 (#98)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1427 | 1416 |
Writing & Preference Too close to call
Gemma 4 26B A4B IT: 58.8 (#110), MiniMax-M2.1: 58.5 (#114)
| Benchmark | Gemma 4 26B A4B IT | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1434 | 1392 |
| LMArena Creative Writing | 1401 | 1362 |
| LMArena Multi-Turn | 1442 | 1396 |
| EQ-Bench Creative Writing | 1305 | — |
Frequently asked questions
Is Gemma 4 26B A4B IT better than MiniMax-M2.1?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 38.4 on the Noometry Index.
Which is cheaper, Gemma 4 26B A4B IT or MiniMax-M2.1?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0765 per million input tokens and $0.26 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is Gemma 4 26B A4B IT or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 38.8 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 26B A4B IT does, with 262K tokens against 205K.
How many benchmarks do Gemma 4 26B A4B IT and MiniMax-M2.1 share?
17 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and MiniMax-M2.1 has 22.