o3 Mini vs Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 leads o3 Mini on the Artificial Analysis Intelligence Index, 12.7 to 12.5, and Qwen3 235B A22B Thinking 2507 costs 1.3x less per output token ($3.50 vs $4.40 per million). Updated October 22, 2026; 37 benchmarks have a result for both.
o3 Mini 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 o3 Mini for a larger context window (200K against 128K tokens) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 37
- o3 Mini only
- 34
- Qwen3 235B A22B Thinking 2507 only
- 9
- Like-for-like categories
- 6 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 12.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3 235B A22B Thinking 2507 has a AA Agentic Index result, 1.3.
Directional only
Reasoning
GPQA Diamond
No call
Only o3 Mini has a GPQA Diamond result, 75.5%.
Directional only
Math
AIME
No call
Only o3 Mini has a AIME result, 86.5%.
Directional only
Knowledge
MMLU Pro
No call
Only o3 Mini has a MMLU Pro result, 78.7%.
Directional only
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
o3 Mini
o3 Mini takes 200K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 235B A22B Thinking 2507
o3 Mini $0.0033, Qwen3 235B A22B Thinking 2507 $0.0022 per turn.
List prices
At a glance
- Coding index
- o3 Mini not benchmarked, Qwen3 235B A22B Thinking 2507 not benchmarked.
- Widest category
- Knowledge, 18.6 points apart on average over 5 shared benchmarks.
- Widest single gap
- SimpleQA Verified: o3 Mini 15.3% against Qwen3 235B A22B Thinking 2507 40.4%, 25.1 points apart on a 0 to 100 scale.
- Output price
- o3 Mini $4.40 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 1.3x apart.
- Context window
- o3 Mini takes 200K 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 | o3 Mini | Bars | Qwen3 235B A22B Thinking 2507 | Ties |
|---|---|---|---|---|
| Coding | 1 | 2 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 5 | ||
| General | 0 | 20 | ||
| All shared boards | 1 | 36 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index12
| Benchmark | o3 Mini | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| Aider polyglot | 60.4% | Not measured | Only o3 Mini measured |
| SWE-bench Verified | 42.4% | Not measured | Only o3 Mini measured |
| SWE-bench Lite | 32.3% | Not measured | Only o3 Mini measured |
| AA Coding Index | Not measured | 22.1 | Only Qwen3 235B A22B Thinking 2507 measured |
| LiveCodeBench (Vals AI) | 71.5% | Not measured | Only o3 Mini measured |
| LiveCodeBench (Artificial Analysis run) | 73.4% | Not measured | Only o3 Mini measured |
| SciCode | 42.8% | Not measured | Only o3 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.8% | Not measured | Only o3 Mini measured |
| GSO-Bench | 1.3% | Not measured | Only o3 Mini measured |
| WeirdML | 43.7% | 41.0% | o3 Mini |
| Cybench | 22.5% | Not measured | Only o3 Mini measured |
| LMArena Text: coding | 1378 | 1424 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: software and IT | 1364 | 1431 | Qwen3 235B A22B Thinking 2507 |
| SciCode | 7.7% | Not measured | Only o3 Mini measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | o3 Mini | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.5 | 12.7 | Qwen3 235B A22B Thinking 2507 |
| Epoch Capabilities Index | 140.2 | Not measured | Only o3 Mini measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | o3 Mini | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.3 | Only Qwen3 235B A22B Thinking 2507 measured |
| τ²-Bench Telecom | 31.3% | Not measured | Only o3 Mini measured |
| Vending-Bench 2 | Not measured | -$11 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | o3 Mini | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| GPQA Diamond | 75.5% | Not measured | Only o3 Mini measured |
| GPQA Diamond (Artificial Analysis run) | 77.3% | Not measured | Only o3 Mini measured |
| Humanity's Last Exam (Artificial Analysis run) | 12.0% | Not measured | Only o3 Mini measured |
| GPQA Diamond (Epoch AI run) | 77.0% | 80.1% | Qwen3 235B A22B Thinking 2507 |
| ARC-AGI | 34.5% | Not measured | Only o3 Mini measured |
| ARC-AGI-2 | 3.0% | Not measured | Only o3 Mini measured |
| SimpleBench | 22.8% | Not measured | Only o3 Mini measured |
| Chess puzzles | 15.0% | Not measured | Only o3 Mini measured |
| Mystery game puzzles | 7.0% | 9.0% | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: hard prompts | 1365 | 1416 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: expert | 1364 | 1463 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: hard prompts in English | 1375 | 1432 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | o3 Mini | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AIME | 86.5% | Not measured | Only o3 Mini measured |
| MATH 500 (Vals AI) | 91.8% | Not measured | Only o3 Mini measured |
| MGSM (Vals AI) | 91.3% | Not measured | Only o3 Mini measured |
| OTIS Mock AIME | 76.9% | 86.7% | Qwen3 235B A22B Thinking 2507 |
| FrontierMath, tiers 1 to 3 | 18.6% | Not measured | Only o3 Mini measured |
| FrontierMath, tier 4 | 0.0% | Not measured | Only o3 Mini measured |
| MATH level 5 | 96.5% | Not measured | Only o3 Mini measured |
| LMArena Text: math | 1396 | 1412 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: mathematical work | 1399 | 1435 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | o3 Mini | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | Not measured | Only o3 Mini measured |
| LegalBench (Vals AI) | 71.5% | Not measured | Only o3 Mini measured |
| CorpFin (Vals AI) | 45.3% | Not measured | Only o3 Mini measured |
| TaxEval (Vals AI) | 69.4% | Not measured | Only o3 Mini measured |
| MedQA (Vals AI) | 94.8% | Not measured | Only o3 Mini measured |
| MMLU Pro (Artificial Analysis run) | 80.2% | Not measured | Only o3 Mini measured |
| SimpleQA Verified | 15.3% | 40.4% | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: science | 1339 | 1433 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: medicine and healthcare | 1330 | 1456 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: legal and government | 1328 | 1415 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: business and finance | 1313 | 1413 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | o3 Mini | 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 index020
| Benchmark | o3 Mini | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| IFBench | 67.1% | Not measured | Only o3 Mini measured |
| Long context reasoning (AA-LCR) | 43.0% | Not measured | Only o3 Mini measured |
| DTBench | 68.8% | 80.3% | Qwen3 235B A22B Thinking 2507 |
| LMCA | 19.0% | 29.3% | Qwen3 235B A22B Thinking 2507 |
| Fiction.LiveBench | 50.0% | 75.0% | Qwen3 235B A22B Thinking 2507 |
| Creative writing (Lech Mazur) | 61.7% | 82.4% | Qwen3 235B A22B Thinking 2507 |
| LMArena Text | 1337 | 1415 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: instruction following | 1337 | 1386 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: creative writing | 1286 | 1384 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: English | 1351 | 1429 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: non-English | 1319 | 1397 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Chinese | 1379 | 1481 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: German | 1303 | 1408 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Japanese | 1286 | 1386 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Korean | 1313 | 1375 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: French | 1334 | Not measured | Only o3 Mini measured |
| LMArena Text: Spanish | 1321 | 1389 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Russian | 1304 | 1401 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Polish | 1294 | 1390 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: multi-turn | 1320 | 1406 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: longer queries | 1343 | 1400 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: writing and language | 1313 | 1388 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: entertainment and media | 1283 | 1370 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | o3 Mini | 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
Qwen3 235B A22B Thinking 2507 costs less
Repository review
50K input + 3K output tokens
Qwen3 235B A22B Thinking 2507 costs less
Agent loop
200K input + 10K output tokens
Qwen3 235B A22B Thinking 2507 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 | OpenAI o3 Mini | Qwen3 235B A22B Thinking 2507 |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | January 31, 2025 | July 25, 2025 |
| Context window | 200K | 128K |
| Input $/Mtok | $1.10 | $0.45 |
| Output $/Mtok | $4.40 | $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 o3 Mini 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 o3 Mini for a larger context window (200K against 128K tokens) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, o3 Mini or Qwen3 235B A22B Thinking 2507?
o3 Mini costs $1.10 per million input tokens and $4.40 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, o3 Mini or Qwen3 235B A22B Thinking 2507?
o3 Mini, with 200K tokens against 128K.
How many benchmarks is the o3 Mini vs Qwen3 235B A22B Thinking 2507 comparison based on?
37 benchmarks have a result for both models as of October 22, 2026. o3 Mini'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.