Gemma 4 31B vs Qwen3 VL 235B A22B Instruct
Gemma 4 31B leads Qwen3 VL 235B A22B Instruct on the Artificial Analysis Intelligence Index, 14.7 to 9.9, and Gemma 4 31B costs 4.7x less per output token ($0.40 vs $1.90 per million). Updated October 22, 2026; 42 benchmarks have a result for both.
Gemma 4 31B or Qwen3 VL 235B A22B Instruct: which to pick
Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; Qwen3 VL 235B A22B Instruct has none, so the two cannot be ranked on coding.
Pick Qwen3 VL 235B A22B Instruct for work measured by LMArena Text: legal and government or LMArena Text: business and finance, where it leads.
- Shared results
- 42
- Gemma 4 31B only
- 29
- Qwen3 VL 235B A22B Instruct 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
No call
Only Gemma 4 31B has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Gemma 4 31B
Gemma 4 31B leads, 14.7 against 9.9.
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
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
Gemma 4 31B $0.0003, Qwen3 VL 235B A22B Instruct $0.0012 per turn.
List prices
At a glance
- Coding index
- Gemma 4 31B 39.0 from 2 benchmarks, Qwen3 VL 235B A22B Instruct not benchmarked.
- Widest category
- Agentic work, 11.4 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench Hard (Artificial Analysis run): Gemma 4 31B 36.4% against Qwen3 VL 235B A22B Instruct 11.4%, 25.0 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 31B $0.40 against Qwen3 VL 235B A22B Instruct $1.90 per million output tokens, 4.7x apart.
- Context window
- Both take 262K 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 | Gemma 4 31B | Bars | Qwen3 VL 235B A22B Instruct | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 7 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 2 | 2 | ||
| General | 21 | 3 | ||
| All shared boards | 37 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | Leader |
|---|---|---|---|
| LiveBench coding | 49.0% | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev | 1367 | Not measured | Only Gemma 4 31B measured |
| AA Coding Index | 43.4 | Not measured | Only Gemma 4 31B measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 64.6% | Only Qwen3 VL 235B A22B Instruct measured |
| SciCode | 45.5% | Not measured | Only Gemma 4 31B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | 11.4% | Gemma 4 31B |
| 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 | 1438 | Gemma 4 31B |
| LMArena Text: software and IT | 1463 | 1442 | Gemma 4 31B |
| LMArena WebDev: React | 1359 | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev: HTML | 1380 | Not measured | Only Gemma 4 31B measured |
| SciCode | 8.9% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.7 | 9.9 | Gemma 4 31B |
| Epoch Capabilities Index | 143.0 | Not measured | Only Gemma 4 31B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | 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% | 54.1% | Gemma 4 31B |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | Leader |
|---|---|---|---|
| LiveBench reasoning | 68.3% | Not measured | Only Gemma 4 31B measured |
| GPQA Diamond (Artificial Analysis run) | 85.7% | 77.2% | Gemma 4 31B |
| Humanity's Last Exam (Artificial Analysis run) | 23.6% | 11.9% | Gemma 4 31B |
| GPQA Diamond (Epoch AI run) | 75.8% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: hard prompts | 1448 | 1428 | Gemma 4 31B |
| LMArena Text: expert | 1464 | 1442 | Gemma 4 31B |
| LMArena Text: hard prompts in English | 1456 | 1439 | Gemma 4 31B |
| LMArena Vision: diagrams | 1283 | 1255 | Gemma 4 31B |
| LMArena Vision: homework | 1310 | 1277 | Gemma 4 31B |
| Kagi LLM Benchmark | 63.5% | Not measured | Only Gemma 4 31B measured |
| 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 | Qwen3 VL 235B A22B Instruct | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 88.3 | Only Qwen3 VL 235B A22B Instruct measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 88.3% | Only Qwen3 VL 235B A22B Instruct measured |
| OTIS Mock AIME | 73.3% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: math | 1463 | 1425 | Gemma 4 31B |
| LMArena Text: mathematical work | 1465 | 1419 | 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 index22
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | 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 | 83.6% | Only Qwen3 VL 235B A22B Instruct measured |
| SimpleQA Verified | 10.4% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: science | 1457 | 1444 | Gemma 4 31B |
| LMArena Text: medicine and healthcare | 1451 | 1431 | Gemma 4 31B |
| LMArena Text: legal and government | 1438 | 1438 | Qwen3 VL 235B A22B Instruct |
| LMArena Text: business and finance | 1430 | 1433 | Qwen3 VL 235B A22B Instruct |
| 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 index1 board, none shared
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | Leader |
|---|---|---|---|
| LiveBench design | 58.4% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index213
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | 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% | 56.5% | Gemma 4 31B |
| Long context reasoning (AA-LCR) | 69.7% | 63.7% | 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 | 1420 | Gemma 4 31B |
| LMArena Text: instruction following | 1433 | 1406 | Gemma 4 31B |
| LMArena Text: creative writing | 1417 | 1366 | Gemma 4 31B |
| LMArena Vision | 1276 | 1247 | Gemma 4 31B |
| LMArena Text: English | 1451 | 1429 | Gemma 4 31B |
| LMArena Text: non-English | 1430 | 1405 | Gemma 4 31B |
| LMArena Text: Chinese | 1475 | 1463 | Gemma 4 31B |
| LMArena Text: German | Not measured | 1424 | Only Qwen3 VL 235B A22B Instruct measured |
| LMArena Text: Japanese | Not measured | 1385 | Only Qwen3 VL 235B A22B Instruct measured |
| LMArena Text: Korean | Not measured | 1394 | Only Qwen3 VL 235B A22B Instruct measured |
| LMArena Text: French | 1436 | 1452 | Qwen3 VL 235B A22B Instruct |
| LMArena Text: Spanish | 1442 | 1428 | Gemma 4 31B |
| LMArena Text: Russian | 1460 | 1408 | Gemma 4 31B |
| LMArena Text: Polish | 1433 | 1419 | Gemma 4 31B |
| LMArena Text: multi-turn | 1452 | 1428 | Gemma 4 31B |
| LMArena Text: longer queries | 1446 | 1419 | Gemma 4 31B |
| LMArena Text: writing and language | 1432 | 1392 | Gemma 4 31B |
| LMArena Text: entertainment and media | 1405 | 1368 | Gemma 4 31B |
| LMArena Vision: English | 1271 | 1256 | Gemma 4 31B |
| LMArena Vision: Chinese | 1326 | 1283 | Gemma 4 31B |
| LMArena Vision: reading text | 1282 | 1253 | Gemma 4 31B |
| LMArena Vision: humor | 1280 | 1209 | Gemma 4 31B |
| LMArena Vision: captioning | 1218 | 1281 | Qwen3 VL 235B A22B Instruct |
| LMArena Vision: recognizing things | 1226 | 1249 | Qwen3 VL 235B A22B Instruct |
| LMArena Vision: creative writing | 1285 | 1220 | Gemma 4 31B |
| LMArena Document | 1425 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 31B | Qwen3 VL 235B A22B Instruct | 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 | Qwen3 VL 235B A22B Instruct |
|---|---|---|
| Maker | Qwen | |
| Weights | Open weights | Open weights |
| Released | April 2, 2026 | September 23, 2025 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.14 | $0.21 |
| Output $/Mtok | $0.40 | $1.90 |
| Coding index | 39.0 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 31B better than Qwen3 VL 235B A22B Instruct for coding?
Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; Qwen3 VL 235B A22B Instruct has none, so the two cannot be ranked on coding. Pick Qwen3 VL 235B A22B Instruct for work measured by LMArena Text: legal and government or LMArena Text: business and finance, where it leads.
Which is cheaper, Gemma 4 31B or Qwen3 VL 235B A22B Instruct?
Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; Qwen3 VL 235B A22B Instruct costs $0.21 and $1.90. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 4 31B or Qwen3 VL 235B A22B Instruct?
Neither: both take 262K tokens.
How many benchmarks is the Gemma 4 31B vs Qwen3 VL 235B A22B Instruct comparison based on?
42 benchmarks have a result for both models as of October 22, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and Qwen3 VL 235B A22B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.