Gemma 3 12B vs Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 leads Gemma 3 12B on the Artificial Analysis Intelligence Index, 12.7 to 3.8, and Gemma 3 12B costs 21.5x less per output token ($0.1625 vs $3.50 per million). Updated October 22, 2026; 29 benchmarks have a result for both.
Gemma 3 12B or Qwen3 235B A22B Thinking 2507: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Gemma 3 12B for output tokens 21.5x cheaper ($0.1625 vs $3.50 per million) and a larger context window (131K against 128K tokens).
- Shared results
- 29
- Gemma 3 12B only
- 14
- Qwen3 235B A22B Thinking 2507 only
- 17
- 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 leads, 12.7 against 3.8.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 leads, 1.3 against 0.1.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3 235B A22B Thinking 2507 has a Design Arena: websites result, 1052.
Directional only
Long documents
Listed context window
Gemma 3 12B
Gemma 3 12B takes 131K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 3 12B
Gemma 3 12B $0.0002, Qwen3 235B A22B Thinking 2507 $0.0022 per turn.
List prices
At a glance
- Coding index
- Gemma 3 12B not benchmarked, Qwen3 235B A22B Thinking 2507 not benchmarked.
- Widest category
- Math, 34.7 points apart on average over 3 shared benchmarks.
- Widest single gap
- OTIS Mock AIME: Gemma 3 12B 16.7% against Qwen3 235B A22B Thinking 2507 86.7%, 70.0 points apart on a 0 to 100 scale.
- Output price
- Gemma 3 12B $0.1625 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 21.5x apart.
- Context window
- Gemma 3 12B takes 131K tokens, Qwen3 235B A22B Thinking 2507 128K.
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 3 12B | Bars | Qwen3 235B A22B Thinking 2507 | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 13 | ||
| All shared boards | 0 | 29 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Coding Index | 5.8 | 22.1 | Qwen3 235B A22B Thinking 2507 |
| LiveCodeBench (Artificial Analysis run) | 13.7% | Not measured | Only Gemma 3 12B measured |
| SciCode | 16.4% | Not measured | Only Gemma 3 12B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 0.8% | Not measured | Only Gemma 3 12B measured |
| WeirdML | Not measured | 41.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: coding | 1281 | 1424 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: software and IT | 1313 | 1431 | Qwen3 235B A22B Thinking 2507 |
| SciCode | 0.0% | Not measured | Only Gemma 3 12B measured |
| 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 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Intelligence Index | 3.8 | 12.7 | Qwen3 235B A22B Thinking 2507 |
| Epoch Capabilities Index | 123.5 | Not measured | Only Gemma 3 12B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.1 | 1.3 | Qwen3 235B A22B Thinking 2507 |
| τ²-Bench Telecom | 10.8% | Not measured | Only Gemma 3 12B measured |
| Vending-Bench 2 | Not measured | -$11 | Only Qwen3 235B A22B Thinking 2507 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 30.4% | Not measured | Only Gemma 3 12B measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 34.9% | Not measured | Only Gemma 3 12B measured |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | Not measured | Only Gemma 3 12B measured |
| GPQA Diamond (Epoch AI run) | 39.5% | 80.1% | Qwen3 235B A22B Thinking 2507 |
| Mystery game puzzles | Not measured | 9.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: hard prompts | 1309 | 1416 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: expert | 1248 | 1463 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: hard prompts in English | 1318 | 1432 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Math Index | 18.3 | Not measured | Only Gemma 3 12B measured |
| AIME 2025 (Artificial Analysis run) | 18.3% | Not measured | Only Gemma 3 12B measured |
| OTIS Mock AIME | 16.7% | 86.7% | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: math | 1307 | 1412 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: mathematical work | 1336 | 1435 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 59.5% | Not measured | Only Gemma 3 12B measured |
| SimpleQA Verified | Not measured | 40.4% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: science | 1366 | 1433 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: medicine and healthcare | 1334 | 1456 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: legal and government | 1381 | 1415 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: business and finance | 1376 | 1413 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1052 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: UI components | Not measured | 942 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: game dev | Not measured | 956 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: data viz | Not measured | 950 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: 3D | Not measured | 997 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: all code categories | Not measured | 1032 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| IFBench | 36.7% | Not measured | Only Gemma 3 12B measured |
| Long context reasoning (AA-LCR) | 8.3% | Not measured | Only Gemma 3 12B measured |
| DTBench | 48.8% | 80.3% | Qwen3 235B A22B Thinking 2507 |
| LMCA | 4.5% | 29.3% | Qwen3 235B A22B Thinking 2507 |
| Fiction.LiveBench | Not measured | 75.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| Creative writing (Lech Mazur) | Not measured | 82.4% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text | 1334 | 1415 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: instruction following | 1299 | 1386 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: creative writing | 1331 | 1384 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: English | 1349 | 1429 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: non-English | 1318 | 1397 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Chinese | Not measured | 1481 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: German | 1370 | 1408 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Japanese | Not measured | 1386 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Korean | Not measured | 1375 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Spanish | Not measured | 1389 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Russian | 1335 | 1401 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Polish | Not measured | 1390 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: multi-turn | 1334 | 1406 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: longer queries | 1317 | 1400 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: writing and language | 1307 | 1388 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: entertainment and media | 1297 | 1370 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 3 12B | Qwen3 235B A22B Thinking 2507 | 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 3 12B costs less
Repository review
50K input + 3K output tokens
Gemma 3 12B costs less
Agent loop
200K input + 10K output tokens
Gemma 3 12B 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 3 12B | Qwen3 235B A22B Thinking 2507 |
|---|---|---|
| Maker | Qwen | |
| Weights | Open weights | Open weights |
| Released | March 13, 2025 | July 25, 2025 |
| Context window | 131K | 128K |
| Input $/Mtok | $0.075 | $0.45 |
| Output $/Mtok | $0.1625 | $3.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 3 12B better than Qwen3 235B A22B Thinking 2507 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 12B for output tokens 21.5x cheaper ($0.1625 vs $3.50 per million) and a larger context window (131K against 128K tokens).
Which is cheaper, Gemma 3 12B or Qwen3 235B A22B Thinking 2507?
Gemma 3 12B costs $0.075 per million input tokens and $0.1625 per million output tokens; Qwen3 235B A22B Thinking 2507 costs $0.45 and $3.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 3 12B or Qwen3 235B A22B Thinking 2507?
Gemma 3 12B, with 131K tokens against 128K.
How many benchmarks is the Gemma 3 12B vs Qwen3 235B A22B Thinking 2507 comparison based on?
29 benchmarks have a result for both models as of October 22, 2026. Gemma 3 12B's coding index rests on 0 independent benchmarks and Qwen3 235B A22B Thinking 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.