Gemini 4 Hydrogen vs MiniMax M3
Gemini 4 Hydrogen leads MiniMax M3 on coding, 77.9 to 33.6 on the Vibe Coding Index, and MiniMax M3 costs 6.3x less per output token ($1.20 vs $7.50 per million). Updated November 14, 2026; 40 benchmarks have a result for both.
Gemini 4 Hydrogen or MiniMax M3: which to pick
Pick Gemini 4 Hydrogen for coding: it scores 77.9 on the Vibe Coding Index against 33.6 for MiniMax M3, though on 4 benchmarks against 5.
Pick MiniMax M3 for output tokens 6.3x cheaper ($1.20 vs $7.50 per million).
- Shared results
- 40
- Gemini 4 Hydrogen only
- 10
- MiniMax M3 only
- 78
- 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
Gemini 4 Hydrogen
Gemini 4 Hydrogen scores 77.9 against 33.6.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only MiniMax M3 has a AA Intelligence Index result, 18.9.
Directional only
Agentic work
AA Agentic Index
No call
Only MiniMax M3 has a AA Agentic Index result, 29.5.
Directional only
Reasoning
GPQA Diamond
No call
Only MiniMax M3 has a GPQA Diamond result, 92.7%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M3 has a MMLU Pro result, 84.2%.
Directional only
Web design
Design Arena: websites
Gemini 4 Hydrogen
Gemini 4 Hydrogen leads, 1320 against 1249.
Same board, both measured
General
Vals Index
No call
Only Gemini 4 Hydrogen has a Vals Index result, 68.5%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M3
Gemini 4 Hydrogen $0.0053, MiniMax M3 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M3 has the number, $0.56.
Directional only
At a glance
- Coding index
- Gemini 4 Hydrogen 77.9 from 4 benchmarks, MiniMax M3 33.6 from 5 benchmarks.
- Widest category
- Coding, 30.2 points apart on average over 9 shared benchmarks.
- Widest single gap
- Terminal-Bench 4 (Vals AI): Gemini 4 Hydrogen 54.0% against MiniMax M3 1.0%, 70.7 points apart on a 0 to 100 scale.
- Output price
- Gemini 4 Hydrogen $7.50 against MiniMax M3 $1.20 per million output tokens, 6.3x apart.
- Context window
- Both take 1.05M tokens.
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 | Gemini 4 Hydrogen | Bars | MiniMax M3 | Ties |
|---|---|---|---|---|
| Coding | 9 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 4 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 40 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index90
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| LiveBench coding | 78.5% | Not measured | Only Gemini 4 Hydrogen measured |
| LMArena WebDev | 1704 | 1484 | Gemini 4 Hydrogen |
| AA Coding Index | Not measured | 58.6 | Only MiniMax M3 measured |
| LiveCodeBench (Vals AI) | Not measured | 82.2% | Only MiniMax M3 measured |
| SWE-bench Verified (Vals AI) | Not measured | 75.0% | Only MiniMax M3 measured |
| Terminal-Bench 4 (Vals AI) | 54.0% | 1.0% | Gemini 4 Hydrogen |
| Vibe Code Bench (Vals AI) | 87.8% | 47.6% | Gemini 4 Hydrogen |
| Code migration (Vals AI) | Not measured | 19.9% | Only MiniMax M3 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 53.6% | Only MiniMax M3 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 33.3% | Only MiniMax M3 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 9.2% | Only MiniMax M3 measured |
| SkillsBench (Vals AI) | Not measured | 51.5% | Only MiniMax M3 measured |
| CyberBench (Vals AI) | Not measured | 65.0% | Only MiniMax M3 measured |
| SciCode | Not measured | 47.1% | Only MiniMax M3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 42.4% | Only MiniMax M3 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 54.0% | 2.0% | Gemini 4 Hydrogen |
| FrontierCode 2.0 | 39.0% | 21.9% | Gemini 4 Hydrogen |
| FrontierCode | Not measured | 14.7% | Only MiniMax M3 measured |
| ALE-Bench | Not measured | 640.0 | Only MiniMax M3 measured |
| LMArena Text: coding | 1516 | 1468 | Gemini 4 Hydrogen |
| LMArena Text: software and IT | 1513 | 1463 | Gemini 4 Hydrogen |
| LMArena WebDev: React | 1724 | 1479 | Gemini 4 Hydrogen |
| LMArena WebDev: HTML | 1743 | 1460 | Gemini 4 Hydrogen |
| LMArena WebDev: from an image | Not measured | 1473 | Only MiniMax M3 measured |
| GameBench 2 | Not measured | 29.0 | Only MiniMax M3 measured |
| Terminal-Bench 4.0 | Not measured | 7.3% | Only MiniMax M3 measured |
| CursorBench 4.0 | 57.8% | Not measured | Only Gemini 4 Hydrogen measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 18.9 | Only MiniMax M3 measured |
| Epoch Capabilities Index | Not measured | 147.7 | Only MiniMax M3 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 29.5 | Only MiniMax M3 measured |
| Design Arena: agents building web apps | Not measured | 1186 | Only MiniMax M3 measured |
| Design Arena: agents building full-stack apps | Not measured | 1175 | Only MiniMax M3 measured |
| Design Arena: agents building mobile apps | Not measured | 1169 | Only MiniMax M3 measured |
| Design Arena: agents building Android apps | Not measured | 1156 | Only MiniMax M3 measured |
| Design Arena: agents building games | Not measured | 1110 | Only MiniMax M3 measured |
| Design Arena: HTML slides | Not measured | 1076 | Only MiniMax M3 measured |
| Design Arena: PowerPoint slides | Not measured | 1171 | Only MiniMax M3 measured |
| Design Arena: spreadsheets | Not measured | 1159 | Only MiniMax M3 measured |
| LiveBench research | 86.8% | Not measured | Only Gemini 4 Hydrogen measured |
| LiveBench browser | 77.1% | Not measured | Only Gemini 4 Hydrogen measured |
| LiveBench long agentic | 61.8% | Not measured | Only Gemini 4 Hydrogen measured |
| Finance Agent (Vals AI) | Not measured | 48.3% | Only MiniMax M3 measured |
| Tax Agent Bench (Vals AI) | 52.3% | 20.6% | Gemini 4 Hydrogen |
| Legal Research Bench (Vals AI) | 53.8% | 29.8% | Gemini 4 Hydrogen |
| Harvey's Legal Agent Benchmark (Vals AI) | 11.3% | Not measured | Only Gemini 4 Hydrogen measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 47.8% | Only MiniMax M3 measured |
| τ²-Bench Telecom | Not measured | 88.9% | Only MiniMax M3 measured |
| APEX-Agents | Not measured | 37.7% | Only MiniMax M3 measured |
| OSWorld 2.0 | Not measured | 4.6% | Only MiniMax M3 measured |
| Vending-Bench 2 | Not measured | $2,158 | Only MiniMax M3 measured |
| Neither model has a result on the other 23 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 92.7% | Only MiniMax M3 measured |
| LiveBench reasoning | 88.6% | Not measured | Only Gemini 4 Hydrogen measured |
| MMMU Pro (Vals AI) | Not measured | 81.2% | Only MiniMax M3 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 92.9% | Only MiniMax M3 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 39.0% | Only MiniMax M3 measured |
| HLE-Diamond (Artificial Analysis run) | 58.8% | 16.0% | Gemini 4 Hydrogen |
| CritPt v2, hard subset (Artificial Analysis run) | 66.0% | 28.0% | Gemini 4 Hydrogen |
| GPQA Diamond (Epoch AI run) | Not measured | 90.9% | Only MiniMax M3 measured |
| SimpleBench | Not measured | 45.8% | Only MiniMax M3 measured |
| Chess puzzles | Not measured | 17.0% | Only MiniMax M3 measured |
| Mystery game puzzles | Not measured | 8.0% | Only MiniMax M3 measured |
| LMArena Text: hard prompts | 1520 | 1442 | Gemini 4 Hydrogen |
| LMArena Text: expert | 1558 | 1460 | Gemini 4 Hydrogen |
| LMArena Text: hard prompts in English | 1514 | 1452 | Gemini 4 Hydrogen |
| LMArena Vision: diagrams | Not measured | 1266 | Only MiniMax M3 measured |
| LMArena Vision: homework | Not measured | 1266 | Only MiniMax M3 measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 71.1% | Only MiniMax M3 measured |
| ProofBench | Not measured | 18.0% | Only MiniMax M3 measured |
| LMArena Text: math | 1507 | 1423 | Gemini 4 Hydrogen |
| LMArena Text: mathematical work | 1534 | 1443 | Gemini 4 Hydrogen |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 84.2% | Only MiniMax M3 measured |
| LegalBench (Vals AI) | Not measured | 85.4% | Only MiniMax M3 measured |
| CorpFin (Vals AI) | Not measured | 68.1% | Only MiniMax M3 measured |
| TaxEval (Vals AI) | Not measured | 72.7% | Only MiniMax M3 measured |
| MortgageTax (Vals AI) | Not measured | 68.4% | Only MiniMax M3 measured |
| MedCode (Vals AI) | Not measured | 46.3% | Only MiniMax M3 measured |
| AA-Omniscience | 46.3 | -5.5 | Gemini 4 Hydrogen |
| LMArena Text: science | 1519 | 1446 | Gemini 4 Hydrogen |
| LMArena Text: medicine and healthcare | 1488 | 1433 | Gemini 4 Hydrogen |
| LMArena Text: legal and government | 1532 | 1430 | Gemini 4 Hydrogen |
| LMArena Text: business and finance | 1486 | 1431 | Gemini 4 Hydrogen |
| Neither model has a result on the other 10 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1320 | 1249 | Gemini 4 Hydrogen |
| Design Arena: UI components | Not measured | 1235 | Only MiniMax M3 measured |
| Design Arena: game dev | 1369 | 1200 | Gemini 4 Hydrogen |
| Design Arena: data viz | Not measured | 1229 | Only MiniMax M3 measured |
| Design Arena: 3D | 1415 | 1189 | Gemini 4 Hydrogen |
| Design Arena: all code categories | 1333 | 1236 | Gemini 4 Hydrogen |
| Design Arena: SVG | Not measured | 1146 | Only MiniMax M3 measured |
| Design Arena: ASCII art | Not measured | 1149 | Only MiniMax M3 measured |
| LiveBench design | 77.3% | Not measured | Only Gemini 4 Hydrogen measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | Leader |
|---|---|---|---|
| Vals Index | 68.5% | Not measured | Only Gemini 4 Hydrogen measured |
| LiveBench data analysis | 83.2% | Not measured | Only Gemini 4 Hydrogen measured |
| Public Benefits Bench (Vals AI) | Not measured | 64.1% | Only MiniMax M3 measured |
| SAGE (Vals AI) | Not measured | 85.5% | Only MiniMax M3 measured |
| MedScribe (Vals AI) | Not measured | 87.3% | Only MiniMax M3 measured |
| Vals Multimodal Index | Not measured | 60.0% | Only MiniMax M3 measured |
| IFBench | Not measured | 82.9% | Only MiniMax M3 measured |
| Long context reasoning (AA-LCR) | Not measured | 83.0% | Only MiniMax M3 measured |
| GDPval-AA | Not measured | 1250 | Only MiniMax M3 measured |
| DTBench | Not measured | 78.9% | Only MiniMax M3 measured |
| LMCA | Not measured | 33.7% | Only MiniMax M3 measured |
| Surface Evolver Bench | Not measured | 55.0% | Only MiniMax M3 measured |
| LMArena Text | 1502 | 1428 | Gemini 4 Hydrogen |
| LMArena Text: instruction following | 1519 | 1428 | Gemini 4 Hydrogen |
| LMArena Text: creative writing | 1509 | 1395 | Gemini 4 Hydrogen |
| LMArena Vision | Not measured | 1249 | Only MiniMax M3 measured |
| LMArena Text: English | 1499 | 1440 | Gemini 4 Hydrogen |
| LMArena Text: non-English | 1495 | 1414 | Gemini 4 Hydrogen |
| LMArena Text: Chinese | 1631 | 1465 | Gemini 4 Hydrogen |
| LMArena Text: German | Not measured | 1429 | Only MiniMax M3 measured |
| LMArena Text: Japanese | Not measured | 1363 | Only MiniMax M3 measured |
| LMArena Text: Korean | Not measured | 1365 | Only MiniMax M3 measured |
| LMArena Text: French | 1512 | 1439 | Gemini 4 Hydrogen |
| LMArena Text: Spanish | 1494 | 1424 | Gemini 4 Hydrogen |
| LMArena Text: Russian | 1492 | 1422 | Gemini 4 Hydrogen |
| LMArena Text: Polish | Not measured | 1417 | Only MiniMax M3 measured |
| LMArena Text: multi-turn | 1485 | 1439 | Gemini 4 Hydrogen |
| LMArena Text: longer queries | 1524 | 1440 | Gemini 4 Hydrogen |
| LMArena Text: writing and language | 1500 | 1411 | Gemini 4 Hydrogen |
| LMArena Text: entertainment and media | 1503 | 1398 | Gemini 4 Hydrogen |
| LMArena Vision: English | Not measured | 1260 | Only MiniMax M3 measured |
| LMArena Vision: Chinese | Not measured | 1310 | Only MiniMax M3 measured |
| LMArena Vision: reading text | Not measured | 1256 | Only MiniMax M3 measured |
| LMArena Vision: humor | Not measured | 1235 | Only MiniMax M3 measured |
| LMArena Vision: recognizing things | Not measured | 1196 | Only MiniMax M3 measured |
| LMArena Vision: creative writing | Not measured | 1232 | Only MiniMax M3 measured |
| LMArena Document | Not measured | 1437 | Only MiniMax M3 measured |
| EQ-Bench 4 | Not measured | 1140 | Only MiniMax M3 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 4 Hydrogen | MiniMax M3 | 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
MiniMax M3 costs less
Repository review
50K input + 3K output tokens
MiniMax M3 costs less
Agent loop
200K input + 10K output tokens
MiniMax M3 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 Gemini 4 Hydrogen | MiniMax M3 |
|---|---|---|
| Maker | MiniMax | |
| Weights | No public weights listed | Open weights |
| Released | November 12, 2026 | May 31, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.50 | $0.30 |
| Output $/Mtok | $7.50 | $1.20 |
| Coding index | 77.9 | 33.6 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | Not computable | $0.56 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Hydrogen better than MiniMax M3 for coding?
Pick Gemini 4 Hydrogen for coding: it scores 77.9 on the Vibe Coding Index against 33.6 for MiniMax M3, though on 4 benchmarks against 5. Pick MiniMax M3 for output tokens 6.3x cheaper ($1.20 vs $7.50 per million).
Which is cheaper, Gemini 4 Hydrogen or MiniMax M3?
Gemini 4 Hydrogen costs $1.50 per million input tokens and $7.50 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M3 only.
Which has the bigger context window, Gemini 4 Hydrogen or MiniMax M3?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 4 Hydrogen vs MiniMax M3 comparison based on?
40 benchmarks have a result for both models as of November 14, 2026. Gemini 4 Hydrogen's coding index rests on 4 independent benchmarks and MiniMax M3's on 5. Where only one model has a result, the page says so instead of naming a winner.