Gemma 4 31B vs Qwen4 Max
Qwen4 Max leads Gemma 4 31B on coding, 74.0 to 21.9 on the Vibe Coding Index, and Gemma 4 31B costs 10.7x less per output token ($0.40 vs $4.275 per million). Updated November 22, 2026; 19 benchmarks have a result for both.
Gemma 4 31B or Qwen4 Max: which to pick
Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 21.9 for Gemma 4 31B.
Pick Gemma 4 31B for output tokens 10.7x cheaper ($0.40 vs $4.275 per million).
- Shared results
- 19
- Gemma 4 31B only
- 58
- Qwen4 Max only
- 7
- 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
Qwen4 Max
Qwen4 Max scores 74.0 against 21.9.
2 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen4 Max
Qwen4 Max leads, 42.9 against 4.4.
Same board, both measured
General
Vals Index
No call
Only Qwen4 Max has a Vals Index result, 63.2%.
Directional only
Long documents
Listed context window
Qwen4 Max
Qwen4 Max takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
Gemma 4 31B $0.0003, Qwen4 Max $0.0036 per turn.
List prices
At a glance
- Coding index
- Gemma 4 31B 21.9 from 2 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
- Widest category
- General, 57.1 points apart on average over 2 shared benchmarks.
- Widest single gap
- GDPval-AA: Gemma 4 31B 627 against Qwen4 Max 1809, 84.1 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 31B $0.40 against Qwen4 Max $4.275 per million output tokens, 10.7x apart.
- Context window
- Gemma 4 31B takes 262K tokens, Qwen4 Max 1M.
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 | Qwen4 Max | Ties |
|---|---|---|---|---|
| Coding | 0 | 8 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 3 | ||
| Reasoning | 0 | 3 | ||
| Knowledge | 0 | 1 | ||
| Web design | 0 | 1 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 19 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index08
| Benchmark | Gemma 4 31B | Qwen4 Max | Leader |
|---|---|---|---|
| LiveBench coding | 20.3% | 69.8% | Qwen4 Max |
| LMArena WebDev | 1370 | 1751 | Qwen4 Max |
| Terminal-Bench 4 (Vals AI) | Not measured | 48.5% | Only Qwen4 Max measured |
| Vibe Code Bench (Vals AI) | Not measured | 86.7% | Only Qwen4 Max measured |
| SciCode | 45.5% | Not measured | Only Gemma 4 31B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | Not measured | Only Gemma 4 31B measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 0.0% | 48.5% | Qwen4 Max |
| FrontierCode 2.0 | 0.0% | 26.5% | Qwen4 Max |
| WeirdML | 52.3% | Not measured | Only Gemma 4 31B measured |
| ALE-Bench | 925.5 | 1831.0 | Qwen4 Max |
| LMArena Text: coding | 1459 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: software and IT | 1463 | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev: React | 1362 | 1785 | Qwen4 Max |
| LMArena WebDev: HTML | 1380 | 1752 | Qwen4 Max |
| LMArena WebDev: from an image | Not measured | 1675 | Only Qwen4 Max measured |
| SciCode | 8.9% | Not measured | Only Gemma 4 31B measured |
| GameBench 2 | 34.9 | 82.4 | Qwen4 Max |
| Neither model has a result on the other 35 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 31B | Qwen4 Max | Leader |
|---|---|---|---|
| AA Intelligence Index | 4.4 | 42.9 | Qwen4 Max |
| Epoch Capabilities Index | 144.1 | Not measured | Only Gemma 4 31B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Gemma 4 31B | Qwen4 Max | Leader |
|---|---|---|---|
| LiveBench research | 38.1% | 84.7% | Qwen4 Max |
| LiveBench browser | 0.0% | 80.7% | Qwen4 Max |
| LiveBench long agentic | 8.5% | 46.6% | Qwen4 Max |
| Tax Agent Bench (Vals AI) | Not measured | 40.4% | Only Qwen4 Max measured |
| Legal Research Bench (Vals AI) | Not measured | 41.4% | Only Qwen4 Max measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 21.3% | Only Qwen4 Max measured |
| τ²-Bench Telecom | 65.5% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Gemma 4 31B | Qwen4 Max | Leader |
|---|---|---|---|
| LiveBench reasoning | 68.3% | 92.2% | Qwen4 Max |
| GPQA Diamond (Artificial Analysis run) | 85.7% | Not measured | Only Gemma 4 31B measured |
| Humanity's Last Exam (Artificial Analysis run) | 23.6% | Not measured | Only Gemma 4 31B measured |
| HLE-Diamond (Artificial Analysis run) | 7.2% | 44.9% | Qwen4 Max |
| CritPt v2, hard subset (Artificial Analysis run) | 4.0% | 43.0% | Qwen4 Max |
| GPQA Diamond (Epoch AI run) | 75.8% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: hard prompts | 1447 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: expert | 1465 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: hard prompts in English | 1456 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: diagrams | 1287 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: homework | 1310 | Not measured | Only Gemma 4 31B measured |
| Kagi LLM Benchmark | 63.5% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Gemma 4 31B | Qwen4 Max | Leader |
|---|---|---|---|
| OTIS Mock AIME | 73.3% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: math | 1461 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: mathematical work | 1464 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 31B | Qwen4 Max | 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 |
| AA-Omniscience | -48.5 | 27.7 | Qwen4 Max |
| SimpleQA Verified | 10.4% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: science | 1455 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: medicine and healthcare | 1450 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: legal and government | 1438 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: business and finance | 1431 | Not measured | Only Gemma 4 31B measured |
| FACTS Benchmark Suite | 50.1% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 31B | Qwen4 Max | Leader |
|---|---|---|---|
| LiveBench design | 56.5% | 79.1% | Qwen4 Max |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemma 4 31B | Qwen4 Max | Leader |
|---|---|---|---|
| Vals Index | Not measured | 63.2% | Only Qwen4 Max measured |
| LiveBench data analysis | 53.3% | 83.4% | Qwen4 Max |
| SAGE (Vals AI) | 82.8% | Not measured | Only Gemma 4 31B measured |
| IFBench | 75.6% | Not measured | Only Gemma 4 31B measured |
| Long context reasoning (AA-LCR) | 69.7% | Not measured | Only Gemma 4 31B measured |
| GDPval-AA | 627 | 1809 | Qwen4 Max |
| 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 | 1442 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: instruction following | 1432 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: creative writing | 1415 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision | 1279 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: English | 1451 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: non-English | 1430 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Chinese | 1476 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: French | 1435 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Spanish | 1443 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Russian | 1460 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Polish | 1431 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: multi-turn | 1452 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: longer queries | 1445 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: writing and language | 1431 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: entertainment and media | 1404 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: English | 1274 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | 1327 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: reading text | 1285 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: humor | 1280 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: captioning | 1210 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | 1228 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | 1287 | Not measured | Only Gemma 4 31B measured |
| LMArena Document | 1434 | Not measured | Only Gemma 4 31B measured |
| EQ-Bench 4 | 1110 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 31B | Qwen4 Max | 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 | Qwen4 Max |
|---|---|---|
| Maker | Qwen | |
| Weights | Open weights | No public weights listed |
| Released | April 2, 2026 | November 16, 2026 |
| Context window | 262K | 1M |
| Input $/Mtok | $0.14 | $1.425 |
| Output $/Mtok | $0.40 | $4.275 |
| Coding index | 21.9 | 74.0 |
| Independent measurements behind it | 2 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 31B better than Qwen4 Max for coding?
Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 21.9 for Gemma 4 31B. Pick Gemma 4 31B for output tokens 10.7x cheaper ($0.40 vs $4.275 per million).
Which is cheaper, Gemma 4 31B or Qwen4 Max?
Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 4 31B or Qwen4 Max?
Qwen4 Max, with 1M tokens against 262K.
How many benchmarks is the Gemma 4 31B vs Qwen4 Max comparison based on?
19 benchmarks have a result for both models as of November 22, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and Qwen4 Max's on 4. Where only one model has a result, the page says so instead of naming a winner.