Gemini 4 Carbon vs Gemma 4 31B
Gemini 4 Carbon leads Gemma 4 31B on coding, 86.6 to 21.9 on the Vibe Coding Index, and Gemma 4 31B costs 25.0x less per output token ($0.40 vs $10.00 per million). Updated November 14, 2026; 45 benchmarks have a result for both.
Gemini 4 Carbon or Gemma 4 31B: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 21.9 for Gemma 4 31B.
Pick Gemma 4 31B for output tokens 25.0x cheaper ($0.40 vs $10.00 per million).
- Shared results
- 45
- Gemini 4 Carbon only
- 28
- Gemma 4 31B only
- 34
- Like-for-like categories
- 8 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 21.9.
4 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 4 Carbon
Gemini 4 Carbon leads, 60.0 against 4.4.
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 Gemini 4 Carbon has a Design Arena: websites result, 1319.
Directional only
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 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
Gemini 4 Carbon $0.0070, Gemma 4 31B $0.0003 per turn.
List prices
At a glance
- Coding index
- Gemini 4 Carbon 86.6 from 4 benchmarks, Gemma 4 31B 21.9 from 2 benchmarks.
- Widest category
- Agentic work, 66.2 points apart on average over 3 shared benchmarks.
- Widest single gap
- LiveBench browser: Gemini 4 Carbon 80.0% against Gemma 4 31B 0.0%, 80.0 points apart on a 0 to 100 scale.
- Output price
- Gemini 4 Carbon $10.00 against Gemma 4 31B $0.40 per million output tokens, 25.0x apart.
- Context window
- Gemini 4 Carbon takes 1.05M tokens, Gemma 4 31B 262K.
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 | Gemma 4 31B | Ties |
|---|---|---|---|---|
| Coding | 9 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 7 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 7 | 0 | ||
| Web design | 1 | 0 | ||
| General | 14 | 0 | ||
| All shared boards | 45 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index90
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench coding | 91.0% | 20.3% | Gemini 4 Carbon |
| LMArena WebDev | 1768 | 1370 | Gemini 4 Carbon |
| AA Coding Index | Not measured | 43.4 | Only Gemma 4 31B measured |
| Terminal-Bench 4 (Vals AI) | 63.1% | Not measured | Only Gemini 4 Carbon measured |
| Vibe Code Bench (Vals AI) | 89.1% | Not measured | Only Gemini 4 Carbon measured |
| SciCode | Not measured | 45.5% | Only Gemma 4 31B measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 36.4% | Only Gemma 4 31B measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 65.2% | 0.0% | Gemini 4 Carbon |
| FrontierCode 2.0 | 40.6% | 0.0% | Gemini 4 Carbon |
| FrontierSWE | 61.2% | Not measured | Only Gemini 4 Carbon measured |
| WeirdML | Not measured | 52.3% | Only Gemma 4 31B measured |
| ALE-Bench | 2374.7 | 925.5 | Gemini 4 Carbon |
| LMArena Text: coding | 1564 | 1459 | Gemini 4 Carbon |
| LMArena Text: software and IT | 1552 | 1463 | Gemini 4 Carbon |
| LMArena WebDev: React | 1792 | 1362 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1770 | 1380 | Gemini 4 Carbon |
| SciCode | Not measured | 8.9% | Only Gemma 4 31B measured |
| GameBench 2 | Not measured | 35.1 | Only Gemma 4 31B measured |
| CursorBench 4.0 | 60.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Intelligence Index | 60.0 | 4.4 | Gemini 4 Carbon |
| Epoch Capabilities Index | 169.8 | 144.3 | Gemini 4 Carbon |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 4.2 | Only Gemma 4 31B 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% | 38.1% | Gemini 4 Carbon |
| LiveBench browser | 80.0% | 0.0% | Gemini 4 Carbon |
| LiveBench long agentic | 72.7% | 8.5% | Gemini 4 Carbon |
| Tax Agent Bench (Vals AI) | 51.8% | Not measured | Only Gemini 4 Carbon measured |
| Legal Research Bench (Vals AI) | 55.8% | Not measured | Only Gemini 4 Carbon measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | Not measured | Only Gemini 4 Carbon measured |
| τ²-Bench Telecom | Not measured | 65.5% | Only Gemma 4 31B measured |
| APEX-Agents | 84.2% | Not measured | Only Gemini 4 Carbon measured |
| Vending-Bench 2 | $16,484 | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench reasoning | 90.6% | 68.3% | Gemini 4 Carbon |
| GPQA Diamond (Artificial Analysis run) | Not measured | 85.7% | Only Gemma 4 31B measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 23.6% | Only Gemma 4 31B measured |
| HLE-Diamond (Artificial Analysis run) | 69.1% | 7.2% | Gemini 4 Carbon |
| CritPt v2, hard subset (Artificial Analysis run) | 69.0% | 4.0% | Gemini 4 Carbon |
| GPQA Diamond (Epoch AI run) | 96.5% | 75.8% | Gemini 4 Carbon |
| 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 | 1447 | Gemini 4 Carbon |
| LMArena Text: expert | 1582 | 1465 | Gemini 4 Carbon |
| LMArena Text: hard prompts in English | 1545 | 1456 | Gemini 4 Carbon |
| LMArena Vision: diagrams | Not measured | 1286 | Only Gemma 4 31B measured |
| LMArena Vision: homework | Not measured | 1310 | Only Gemma 4 31B measured |
| Kagi LLM Benchmark | Not measured | 63.5% | Only Gemma 4 31B measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 73.3% | Gemini 4 Carbon |
| 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 |
| LMArena Text: math | Not measured | 1462 | Only Gemma 4 31B measured |
| LMArena Text: mathematical work | 1538 | 1464 | Gemini 4 Carbon |
| MathArena | 85.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | Not measured | 52.6% | Only Gemma 4 31B measured |
| MortgageTax (Vals AI) | Not measured | 61.4% | Only Gemma 4 31B measured |
| AA-Omniscience | 53.5 | -48.5 | Gemini 4 Carbon |
| SimpleQA Verified | 77.7% | 10.4% | Gemini 4 Carbon |
| LMArena Text: science | 1535 | 1456 | Gemini 4 Carbon |
| LMArena Text: medicine and healthcare | 1525 | 1450 | Gemini 4 Carbon |
| LMArena Text: legal and government | 1542 | 1438 | Gemini 4 Carbon |
| LMArena Text: business and finance | 1520 | 1431 | Gemini 4 Carbon |
| FACTS Benchmark Suite | 78.4% | 50.1% | Gemini 4 Carbon |
| PRBench Legal | 53.3% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| Design Arena: websites | 1319 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: UI components | 1357 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: game dev | 1326 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: 3D | 1434 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: all code categories | 1348 | Not measured | Only Gemini 4 Carbon measured |
| LiveBench design | 80.2% | 56.5% | Gemini 4 Carbon |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index140
| Benchmark | Gemini 4 Carbon | Gemma 4 31B | Leader |
|---|---|---|---|
| Vals Index | 70.5% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench data analysis | 86.5% | 53.3% | Gemini 4 Carbon |
| SAGE (Vals AI) | Not measured | 82.8% | Only Gemma 4 31B measured |
| IFBench | Not measured | 75.6% | Only Gemma 4 31B measured |
| Long context reasoning (AA-LCR) | 79.3% | 69.7% | Gemini 4 Carbon |
| GDPval-AA | 1733 | 627 | Gemini 4 Carbon |
| DTBench | Not measured | 82.7% | Only Gemma 4 31B measured |
| LMCA | Not measured | 39.3% | Only Gemma 4 31B measured |
| Surface Evolver Bench | Not measured | 30.6% | Only Gemma 4 31B measured |
| Furniture assembly | 77.5% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text | 1538 | 1443 | Gemini 4 Carbon |
| LMArena Text: instruction following | 1539 | 1433 | Gemini 4 Carbon |
| LMArena Text: creative writing | 1533 | 1415 | Gemini 4 Carbon |
| LMArena Vision | Not measured | 1279 | Only Gemma 4 31B measured |
| LMArena Text: English | 1530 | 1451 | Gemini 4 Carbon |
| LMArena Text: non-English | 1534 | 1430 | Gemini 4 Carbon |
| LMArena Text: Chinese | 1613 | 1476 | Gemini 4 Carbon |
| LMArena Text: French | Not measured | 1434 | Only Gemma 4 31B measured |
| LMArena Text: Spanish | Not measured | 1444 | Only Gemma 4 31B measured |
| LMArena Text: Russian | 1560 | 1460 | Gemini 4 Carbon |
| LMArena Text: Polish | Not measured | 1431 | Only Gemma 4 31B measured |
| LMArena Text: multi-turn | 1569 | 1452 | Gemini 4 Carbon |
| LMArena Text: longer queries | 1549 | 1445 | Gemini 4 Carbon |
| LMArena Text: writing and language | 1542 | 1431 | Gemini 4 Carbon |
| LMArena Text: entertainment and media | 1527 | 1405 | Gemini 4 Carbon |
| LMArena Vision: English | Not measured | 1272 | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | Not measured | 1327 | Only Gemma 4 31B measured |
| LMArena Vision: reading text | Not measured | 1285 | Only Gemma 4 31B measured |
| LMArena Vision: humor | Not measured | 1280 | Only Gemma 4 31B measured |
| LMArena Vision: captioning | Not measured | 1209 | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | Not measured | 1227 | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | Not measured | 1286 | Only Gemma 4 31B measured |
| LMArena Document | Not measured | 1434 | Only Gemma 4 31B measured |
| EQ-Bench 4 | Not measured | 1110 | 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 | Gemini 4 Carbon | Gemma 4 31B | 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 Gemini 4 Carbon | Google Gemma 4 31B |
|---|---|---|
| Maker | ||
| Weights | No public weights listed | Open weights |
| Released | November 10, 2026 | April 2, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $2.00 | $0.14 |
| Output $/Mtok | $10.00 | $0.40 |
| Coding index | 86.6 | 21.9 |
| Independent measurements behind it | 4 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Carbon better than Gemma 4 31B for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 21.9 for Gemma 4 31B. Pick Gemma 4 31B for output tokens 25.0x cheaper ($0.40 vs $10.00 per million).
Which is cheaper, Gemini 4 Carbon or Gemma 4 31B?
Gemini 4 Carbon costs $2.00 per million input tokens and $10.00 per million output tokens; Gemma 4 31B costs $0.14 and $0.40. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemini 4 Carbon or Gemma 4 31B?
Gemini 4 Carbon, with 1.05M tokens against 262K.
How many benchmarks is the Gemini 4 Carbon vs Gemma 4 31B comparison based on?
45 benchmarks have a result for both models as of November 14, 2026. Gemini 4 Carbon's coding index rests on 4 independent benchmarks and Gemma 4 31B's on 2. Where only one model has a result, the page says so instead of naming a winner.