Gemma 4 31B vs MiniMax M2
MiniMax M2 leads Gemma 4 31B on the Artificial Analysis Intelligence Index, 18.6 to 14.7, and Gemma 4 31B costs 2.5x less per output token ($0.40 vs $1.02 per million). Updated October 22, 2026; 35 benchmarks have a result for both.
Gemma 4 31B or MiniMax M2: which to pick
Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; MiniMax M2 has none, so the two cannot be ranked on coding.
Pick MiniMax M2 for work measured by AA Intelligence Index or τ²-Bench Telecom, where it leads.
- Shared results
- 35
- Gemma 4 31B only
- 36
- MiniMax M2 only
- 15
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Gemma 4 31B has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M2
MiniMax M2 leads, 18.6 against 14.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemma 4 31B has a AA Agentic Index result, 4.2.
Directional only
Web design
Design Arena: websites
No call
Only MiniMax M2 has a Design Arena: websites result, 1143.
Directional only
Long documents
Listed context window
Gemma 4 31B
Gemma 4 31B takes 262K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
Gemma 4 31B $0.0003, MiniMax M2 $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2 has the number, $0.702.
Directional only
At a glance
- Coding index
- Gemma 4 31B 39.0 from 2 benchmarks, MiniMax M2 not benchmarked.
- Widest category
- Agentic work, 21.3 points apart on average over 1 shared benchmark.
- Widest single gap
- LMArena Text: writing and language: Gemma 4 31B 1432 against MiniMax M2 1295, 22.8 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 31B $0.40 against MiniMax M2 $1.02 per million output tokens, 2.5x apart.
- Context window
- Gemma 4 31B takes 262K tokens, MiniMax M2 205K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemma 4 31B | Bars | MiniMax M2 | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 6 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 16 | 0 | ||
| All shared boards | 33 | 2 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 61.0% | Only MiniMax M2 measured |
| LiveBench coding | 49.0% | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev | 1367 | 1297 | Gemma 4 31B |
| AA Coding Index | 43.4 | Not measured | Only Gemma 4 31B measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 82.6% | Only MiniMax M2 measured |
| SciCode | 45.5% | Not measured | Only Gemma 4 31B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | 25.8% | Gemma 4 31B |
| Terminal-Bench | Not measured | 30.0% | Only MiniMax M2 measured |
| WeirdML | 52.3% | Not measured | Only Gemma 4 31B measured |
| ALE-Bench | 925.5 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: coding | 1459 | 1371 | Gemma 4 31B |
| LMArena Text: software and IT | 1463 | 1373 | Gemma 4 31B |
| LMArena WebDev: React | 1359 | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev: HTML | 1380 | 1306 | Gemma 4 31B |
| SciCode | 8.9% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.7 | 18.6 | MiniMax M2 |
| Epoch Capabilities Index | 143.0 | Not measured | Only Gemma 4 31B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| AA Agentic Index | 4.2 | Not measured | Only Gemma 4 31B measured |
| LiveBench research | 44.4% | Not measured | Only Gemma 4 31B measured |
| LiveBench browser | 4.0% | Not measured | Only Gemma 4 31B measured |
| LiveBench long agentic | 13.3% | Not measured | Only Gemma 4 31B measured |
| τ²-Bench Telecom | 65.5% | 86.8% | MiniMax M2 |
| Vending-Bench 2 | Not measured | $161 | Only MiniMax M2 measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| LiveBench reasoning | 68.3% | Not measured | Only Gemma 4 31B measured |
| GPQA Diamond (Artificial Analysis run) | 85.7% | 77.7% | Gemma 4 31B |
| Humanity's Last Exam (Artificial Analysis run) | 23.6% | 13.7% | Gemma 4 31B |
| GPQA Diamond (Epoch AI run) | 75.8% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: hard prompts | 1448 | 1357 | Gemma 4 31B |
| LMArena Text: expert | 1464 | 1338 | Gemma 4 31B |
| LMArena Text: hard prompts in English | 1456 | 1376 | Gemma 4 31B |
| LMArena Vision: diagrams | 1283 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: homework | 1310 | Not measured | Only Gemma 4 31B measured |
| Kagi LLM Benchmark | 63.5% | 57.8% | Gemma 4 31B |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 78.3 | Only MiniMax M2 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 78.3% | Only MiniMax M2 measured |
| OTIS Mock AIME | 73.3% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: math | 1463 | 1351 | Gemma 4 31B |
| LMArena Text: mathematical work | 1465 | 1368 | Gemma 4 31B |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 52.6% | Not measured | Only Gemma 4 31B measured |
| MortgageTax (Vals AI) | 61.4% | Not measured | Only Gemma 4 31B measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 82.0% | Only MiniMax M2 measured |
| SimpleQA Verified | 10.4% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: science | 1457 | 1348 | Gemma 4 31B |
| LMArena Text: medicine and healthcare | 1451 | 1367 | Gemma 4 31B |
| LMArena Text: legal and government | 1438 | 1349 | Gemma 4 31B |
| LMArena Text: business and finance | 1430 | 1336 | Gemma 4 31B |
| FACTS Benchmark Suite | 45.3% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1143 | Only MiniMax M2 measured |
| Design Arena: UI components | Not measured | 1137 | Only MiniMax M2 measured |
| Design Arena: game dev | Not measured | 1118 | Only MiniMax M2 measured |
| Design Arena: data viz | Not measured | 1140 | Only MiniMax M2 measured |
| Design Arena: 3D | Not measured | 1098 | Only MiniMax M2 measured |
| Design Arena: all code categories | Not measured | 1135 | Only MiniMax M2 measured |
| Design Arena: SVG | Not measured | 1100 | Only MiniMax M2 measured |
| LiveBench design | 58.4% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index160
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| LiveBench data analysis | 53.3% | Not measured | Only Gemma 4 31B measured |
| SAGE (Vals AI) | 55.0% | Not measured | Only Gemma 4 31B measured |
| IFBench | 75.6% | 72.3% | Gemma 4 31B |
| Long context reasoning (AA-LCR) | 69.7% | 64.3% | Gemma 4 31B |
| DTBench | 82.7% | Not measured | Only Gemma 4 31B measured |
| LMCA | 39.3% | Not measured | Only Gemma 4 31B measured |
| Surface Evolver Bench | 30.6% | Not measured | Only Gemma 4 31B measured |
| LMArena Text | 1443 | 1340 | Gemma 4 31B |
| LMArena Text: instruction following | 1433 | 1329 | Gemma 4 31B |
| LMArena Text: creative writing | 1417 | 1286 | Gemma 4 31B |
| LMArena Vision | 1276 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: English | 1451 | 1364 | Gemma 4 31B |
| LMArena Text: non-English | 1430 | 1313 | Gemma 4 31B |
| LMArena Text: Chinese | 1475 | 1366 | Gemma 4 31B |
| LMArena Text: German | Not measured | 1357 | Only MiniMax M2 measured |
| LMArena Text: French | 1436 | 1336 | Gemma 4 31B |
| LMArena Text: Spanish | 1442 | 1326 | Gemma 4 31B |
| LMArena Text: Russian | 1460 | 1330 | Gemma 4 31B |
| LMArena Text: Polish | 1433 | 1312 | Gemma 4 31B |
| LMArena Text: multi-turn | 1452 | 1361 | Gemma 4 31B |
| LMArena Text: longer queries | 1446 | 1331 | Gemma 4 31B |
| LMArena Text: writing and language | 1432 | 1295 | Gemma 4 31B |
| LMArena Text: entertainment and media | 1405 | 1298 | Gemma 4 31B |
| LMArena Vision: English | 1271 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | 1326 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: reading text | 1282 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: humor | 1280 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: captioning | 1218 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | 1226 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | 1285 | Not measured | Only Gemma 4 31B measured |
| LMArena Document | 1425 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 31B | MiniMax M2 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 4 31B costs less
Repository review
50K input + 3K output tokens
Gemma 4 31B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 31B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemma 4 31B | MiniMax M2 |
|---|---|---|
| Maker | MiniMax | |
| Weights | Open weights | Open weights |
| Released | April 2, 2026 | October 23, 2025 |
| Context window | 262K | 205K |
| Input $/Mtok | $0.14 | $0.255 |
| Output $/Mtok | $0.40 | $1.02 |
| Coding index | 39.0 | Not benchmarked |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | $0.702 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 31B better than MiniMax M2 for coding?
Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; MiniMax M2 has none, so the two cannot be ranked on coding. Pick MiniMax M2 for work measured by AA Intelligence Index or τ²-Bench Telecom, where it leads.
Which is cheaper, Gemma 4 31B or MiniMax M2?
Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; MiniMax M2 costs $0.255 and $1.02. Cost per solved task is known for MiniMax M2 only.
Which has the bigger context window, Gemma 4 31B or MiniMax M2?
Gemma 4 31B, with 262K tokens against 205K.
How many benchmarks is the Gemma 4 31B vs MiniMax M2 comparison based on?
35 benchmarks have a result for both models as of October 22, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and MiniMax M2's on 1. Where only one model has a result, the page says so instead of naming a winner.