Gemini 4 Carbon vs MiniMax M2.7
Gemini 4 Carbon leads MiniMax M2.7 on coding, 86.6 to 36.2 on the Vibe Coding Index, and MiniMax M2.7 costs 7.6x less per output token ($1.32 vs $10.00 per million). Updated November 14, 2026; 36 benchmarks have a result for both.
Gemini 4 Carbon or MiniMax M2.7: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 36.2 for MiniMax M2.7.
Pick MiniMax M2.7 for output tokens 7.6x cheaper ($1.32 vs $10.00 per million).
- Shared results
- 36
- Gemini 4 Carbon only
- 37
- MiniMax M2.7 only
- 40
- 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 Carbon
Gemini 4 Carbon scores 86.6 against 36.2.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Gemini 4 Carbon has a AA Intelligence Index result, 60.0.
Directional only
Agentic work
AA Agentic Index
No call
Only MiniMax M2.7 has a AA Agentic Index result, 15.3.
Directional only
Reasoning
GPQA Diamond
No call
Only MiniMax M2.7 has a GPQA Diamond result, 86.6%.
Directional only
Math
AIME
No call
Only MiniMax M2.7 has a AIME result, 91.0%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M2.7 has a MMLU Pro result, 80.4%.
Directional only
Web design
Design Arena: websites
Gemini 4 Carbon
Gemini 4 Carbon leads, 1319 against 1234.
Same board, both measured
General
Vals Index
No call
Only Gemini 4 Carbon has a Vals Index result, 70.5%.
Directional only
Long documents
Listed context window
Gemini 4 Carbon
Gemini 4 Carbon takes 1.05M tokens against 197K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.7
Gemini 4 Carbon $0.0070, MiniMax M2.7 $0.0011 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.7 has the number, $0.64.
Directional only
At a glance
- Coding index
- Gemini 4 Carbon 86.6 from 4 benchmarks, MiniMax M2.7 36.2 from 3 benchmarks.
- Widest category
- Agentic work, 45.1 points apart on average over 2 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Gemini 4 Carbon 89.1% against MiniMax M2.7 11.9%, 77.1 points apart on a 0 to 100 scale.
- Output price
- Gemini 4 Carbon $10.00 against MiniMax M2.7 $1.32 per million output tokens, 7.6x apart.
- Context window
- Gemini 4 Carbon takes 1.05M tokens, MiniMax M2.7 197K.
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 Carbon | Bars | MiniMax M2.7 | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 4 | 0 | ||
| Web design | 5 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 36 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| LiveBench coding | 91.0% | Not measured | Only Gemini 4 Carbon measured |
| LMArena WebDev | 1768 | 1398 | Gemini 4 Carbon |
| AA Coding Index | Not measured | 52.6 | Only MiniMax M2.7 measured |
| LiveCodeBench (Vals AI) | Not measured | 79.9% | Only MiniMax M2.7 measured |
| SWE-bench Verified (Vals AI) | Not measured | 73.8% | Only MiniMax M2.7 measured |
| Terminal-Bench 4 (Vals AI) | 63.1% | Not measured | Only Gemini 4 Carbon measured |
| Vibe Code Bench (Vals AI) | 89.1% | 11.9% | Gemini 4 Carbon |
| Code migration (Vals AI) | Not measured | 8.7% | Only MiniMax M2.7 measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only MiniMax M2.7 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 48.7% | Only MiniMax M2.7 measured |
| SciCode | Not measured | 50.1% | Only MiniMax M2.7 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 39.4% | Only MiniMax M2.7 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 65.2% | 0.0% | Gemini 4 Carbon |
| FrontierCode 2.0 | 40.6% | Not measured | Only Gemini 4 Carbon measured |
| Terminal-Bench | Not measured | 45.1% | Only MiniMax M2.7 measured |
| FrontierSWE | 61.2% | Not measured | Only Gemini 4 Carbon measured |
| WeirdML | Not measured | 37.0% | Only MiniMax M2.7 measured |
| ALE-Bench | 2374.7 | 599.3 | Gemini 4 Carbon |
| LMArena Text: coding | 1564 | 1453 | Gemini 4 Carbon |
| LMArena Text: software and IT | 1552 | 1446 | Gemini 4 Carbon |
| LMArena WebDev: React | 1792 | 1386 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1770 | 1401 | Gemini 4 Carbon |
| Terminal-Bench 2.0 | Not measured | 45.1% | Only MiniMax M2.7 measured |
| CursorBench 4.0 | 60.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| AA Intelligence Index | 60.0 | Not measured | Only Gemini 4 Carbon measured |
| Epoch Capabilities Index | 169.8 | Not measured | Only Gemini 4 Carbon measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 15.3 | Only MiniMax M2.7 measured |
| Design Arena: agents building mobile apps | 1284 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: spreadsheets | 1224 | Not measured | Only Gemini 4 Carbon measured |
| LiveBench research | 92.5% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench browser | 80.0% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench long agentic | 72.7% | Not measured | Only Gemini 4 Carbon measured |
| Finance Agent (Vals AI) | Not measured | 27.9% | Only MiniMax M2.7 measured |
| Tax Agent Bench (Vals AI) | 51.8% | 6.9% | Gemini 4 Carbon |
| Legal Research Bench (Vals AI) | 55.8% | 10.6% | Gemini 4 Carbon |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | Not measured | Only Gemini 4 Carbon measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 28.4% | Only MiniMax M2.7 measured |
| τ²-Bench Telecom | Not measured | 84.8% | Only MiniMax M2.7 measured |
| APEX-Agents | 84.2% | Not measured | Only Gemini 4 Carbon measured |
| Vending-Bench 2 | $16,484 | Not measured | Only Gemini 4 Carbon measured |
| Toolathlon-Verified | Not measured | 47.5% | Only MiniMax M2.7 measured |
| Neither model has a result on the other 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 86.6% | Only MiniMax M2.7 measured |
| LiveBench reasoning | 90.6% | Not measured | Only Gemini 4 Carbon measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 87.4% | Only MiniMax M2.7 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 29.6% | Only MiniMax M2.7 measured |
| HLE-Diamond (Artificial Analysis run) | 69.1% | Not measured | Only Gemini 4 Carbon measured |
| CritPt v2, hard subset (Artificial Analysis run) | 69.0% | Not measured | Only Gemini 4 Carbon measured |
| GPQA Diamond (Epoch AI run) | 96.5% | Not measured | Only Gemini 4 Carbon measured |
| ARC-AGI | 98.5% | Not measured | Only Gemini 4 Carbon measured |
| ARC-AGI-2 | 94.2% | Not measured | Only Gemini 4 Carbon measured |
| SimpleBench | 92.6% | Not measured | Only Gemini 4 Carbon measured |
| Chess puzzles | 78.0% | Not measured | Only Gemini 4 Carbon measured |
| Mystery game puzzles | 73.0% | Not measured | Only Gemini 4 Carbon measured |
| EBR-bench | 87.6% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: hard prompts | 1551 | 1422 | Gemini 4 Carbon |
| LMArena Text: expert | 1582 | 1443 | Gemini 4 Carbon |
| LMArena Text: hard prompts in English | 1545 | 1440 | Gemini 4 Carbon |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| AIME | Not measured | 91.0% | Only MiniMax M2.7 measured |
| OTIS Mock AIME | 100.0% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tiers 1 to 3 | 90.5% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tier 4 | 95.1% | Not measured | Only Gemini 4 Carbon measured |
| ProofBench | Not measured | 3.0% | Only MiniMax M2.7 measured |
| LMArena Text: math | Not measured | 1422 | Only MiniMax M2.7 measured |
| LMArena Text: mathematical work | 1538 | 1437 | Gemini 4 Carbon |
| MathArena | 85.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 80.4% | Only MiniMax M2.7 measured |
| LegalBench (Vals AI) | Not measured | 84.0% | Only MiniMax M2.7 measured |
| CaseLaw (Vals AI) | Not measured | 60.9% | Only MiniMax M2.7 measured |
| CorpFin (Vals AI) | Not measured | 61.2% | Only MiniMax M2.7 measured |
| TaxEval (Vals AI) | Not measured | 66.6% | Only MiniMax M2.7 measured |
| MedCode (Vals AI) | Not measured | 34.4% | Only MiniMax M2.7 measured |
| AA-Omniscience | 53.5 | Not measured | Only Gemini 4 Carbon measured |
| SimpleQA Verified | 77.7% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: science | 1535 | 1416 | Gemini 4 Carbon |
| LMArena Text: medicine and healthcare | 1525 | 1410 | Gemini 4 Carbon |
| LMArena Text: legal and government | 1542 | 1402 | Gemini 4 Carbon |
| LMArena Text: business and finance | 1520 | 1407 | Gemini 4 Carbon |
| FACTS Benchmark Suite | 78.4% | Not measured | Only Gemini 4 Carbon measured |
| PRBench Legal | 53.3% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| Design Arena: websites | 1319 | 1234 | Gemini 4 Carbon |
| Design Arena: UI components | 1357 | 1202 | Gemini 4 Carbon |
| Design Arena: game dev | 1326 | 1198 | Gemini 4 Carbon |
| Design Arena: data viz | Not measured | 1229 | Only MiniMax M2.7 measured |
| Design Arena: 3D | 1434 | 1175 | Gemini 4 Carbon |
| Design Arena: all code categories | 1348 | 1223 | Gemini 4 Carbon |
| Design Arena: SVG | Not measured | 1123 | Only MiniMax M2.7 measured |
| Design Arena: ASCII art | Not measured | 1129 | Only MiniMax M2.7 measured |
| LiveBench design | 80.2% | Not measured | Only Gemini 4 Carbon measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | Leader |
|---|---|---|---|
| Vals Index | 70.5% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench data analysis | 86.5% | Not measured | Only Gemini 4 Carbon measured |
| MedScribe (Vals AI) | Not measured | 79.9% | Only MiniMax M2.7 measured |
| IFBench | Not measured | 75.7% | Only MiniMax M2.7 measured |
| Long context reasoning (AA-LCR) | 79.3% | 78.3% | Gemini 4 Carbon |
| GDPval-AA | 1733 | 1015 | Gemini 4 Carbon |
| Furniture assembly | 77.5% | Not measured | Only Gemini 4 Carbon measured |
| ExploitBench | Not measured | 13.3% | Only MiniMax M2.7 measured |
| LMArena Text | 1538 | 1405 | Gemini 4 Carbon |
| LMArena Text: instruction following | 1539 | 1405 | Gemini 4 Carbon |
| LMArena Text: creative writing | 1533 | 1354 | Gemini 4 Carbon |
| LMArena Text: English | 1530 | 1425 | Gemini 4 Carbon |
| LMArena Text: non-English | 1534 | 1383 | Gemini 4 Carbon |
| LMArena Text: Chinese | 1613 | 1439 | Gemini 4 Carbon |
| LMArena Text: German | Not measured | 1398 | Only MiniMax M2.7 measured |
| LMArena Text: Japanese | Not measured | 1252 | Only MiniMax M2.7 measured |
| LMArena Text: Korean | Not measured | 1314 | Only MiniMax M2.7 measured |
| LMArena Text: French | Not measured | 1425 | Only MiniMax M2.7 measured |
| LMArena Text: Spanish | Not measured | 1406 | Only MiniMax M2.7 measured |
| LMArena Text: Russian | 1560 | 1383 | Gemini 4 Carbon |
| LMArena Text: Polish | Not measured | 1386 | Only MiniMax M2.7 measured |
| LMArena Text: multi-turn | 1569 | 1412 | Gemini 4 Carbon |
| LMArena Text: longer queries | 1549 | 1418 | Gemini 4 Carbon |
| LMArena Text: writing and language | 1542 | 1376 | Gemini 4 Carbon |
| LMArena Text: entertainment and media | 1527 | 1360 | Gemini 4 Carbon |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 4 Carbon | MiniMax M2.7 | 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 M2.7 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.7 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.7 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 Carbon | MiniMax M2.7 |
|---|---|---|
| Maker | MiniMax | |
| Weights | No public weights listed | Open weights |
| Released | November 10, 2026 | March 18, 2026 |
| Context window | 1.05M | 197K |
| Input $/Mtok | $2.00 | $0.405 |
| Output $/Mtok | $10.00 | $1.32 |
| Coding index | 86.6 | 36.2 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | $0.64 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Carbon better than MiniMax M2.7 for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 36.2 for MiniMax M2.7. Pick MiniMax M2.7 for output tokens 7.6x cheaper ($1.32 vs $10.00 per million).
Which is cheaper, Gemini 4 Carbon or MiniMax M2.7?
Gemini 4 Carbon costs $2.00 per million input tokens and $10.00 per million output tokens; MiniMax M2.7 costs $0.405 and $1.32. Cost per solved task is known for MiniMax M2.7 only.
Which has the bigger context window, Gemini 4 Carbon or MiniMax M2.7?
Gemini 4 Carbon, with 1.05M tokens against 197K.
How many benchmarks is the Gemini 4 Carbon vs MiniMax M2.7 comparison based on?
36 benchmarks have a result for both models as of November 14, 2026. Gemini 4 Carbon's coding index rests on 4 independent benchmarks and MiniMax M2.7's on 3. Where only one model has a result, the page says so instead of naming a winner.