Qwen2.5 Coder 32B Instruct vs Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507 leads Qwen2.5 Coder 32B Instruct on the Artificial Analysis Intelligence Index, 12.0 to 6.7, and Qwen3 235B A22B Instruct 2507 costs 1.3x less per output token ($0.75 vs $1.00 per million). Updated October 22, 2026; 5 benchmarks have a result for both.
Qwen2.5 Coder 32B Instruct or Qwen3 235B A22B Instruct 2507: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen2.5 Coder 32B Instruct for work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 5
- Qwen2.5 Coder 32B Instruct only
- 30
- Qwen3 235B A22B Instruct 2507 only
- 19
- Like-for-like categories
- 4 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 Instruct 2507
Qwen3 235B A22B Instruct 2507 leads, 12.0 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3 235B A22B Instruct 2507 has a Design Arena: websites result, 1058.
Directional only
Long documents
Listed context window
Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507 takes 262K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 235B A22B Instruct 2507
Qwen2.5 Coder 32B Instruct $0.0012, Qwen3 235B A22B Instruct 2507 $0.0005 per turn.
List prices
At a glance
- Coding index
- Qwen2.5 Coder 32B Instruct not benchmarked, Qwen3 235B A22B Instruct 2507 not benchmarked.
- Widest category
- Coding, 49.3 points apart on average over 1 shared benchmark.
- Widest single gap
- LiveCodeBench (Artificial Analysis run): Qwen2.5 Coder 32B Instruct 29.5% against Qwen3 235B A22B Instruct 2507 78.8%, 49.3 points apart on a 0 to 100 scale.
- Output price
- Qwen2.5 Coder 32B Instruct $1.00 against Qwen3 235B A22B Instruct 2507 $0.75 per million output tokens, 1.3x apart.
- Context window
- Qwen2.5 Coder 32B Instruct takes 33K tokens, Qwen3 235B A22B Instruct 2507 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 | Qwen2.5 Coder 32B Instruct | Bars | Qwen3 235B A22B Instruct 2507 | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| Knowledge | 0 | 1 | ||
| All shared boards | 0 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| Aider polyglot | 16.4% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| SWE-bench Verified | 47.0% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LiveCodeBench (Artificial Analysis run) | 29.5% | 78.8% | Qwen3 235B A22B Instruct 2507 |
| SciCode | Not measured | 41.4% | Only Qwen3 235B A22B Instruct 2507 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 15.2% | Only Qwen3 235B A22B Instruct 2507 measured |
| WeirdML | Not measured | 38.7% | Only Qwen3 235B A22B Instruct 2507 measured |
| LMArena Text: coding | 1276 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: software and IT | 1261 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 12.0 | Qwen3 235B A22B Instruct 2507 |
| Epoch Capabilities Index | 119.5 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 53.2% | Only Qwen3 235B A22B Instruct 2507 measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 52.1% | Only Qwen3 235B A22B Instruct 2507 measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 41.7% | 79.0% | Qwen3 235B A22B Instruct 2507 |
| Humanity's Last Exam (Artificial Analysis run) | 3.5% | 15.9% | Qwen3 235B A22B Instruct 2507 |
| ARC-AGI | Not measured | 11.0% | Only Qwen3 235B A22B Instruct 2507 measured |
| ARC-AGI-2 | Not measured | 1.3% | Only Qwen3 235B A22B Instruct 2507 measured |
| LMArena Text: hard prompts | 1251 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: expert | 1221 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: hard prompts in English | 1269 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 91.0 | Only Qwen3 235B A22B Instruct 2507 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 91.0% | Only Qwen3 235B A22B Instruct 2507 measured |
| GSM8K | 93.0% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: math | 1251 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: mathematical work | 1243 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 63.5% | 84.3% | Qwen3 235B A22B Instruct 2507 |
| MMLU | 79.1% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| AI2 Reasoning Challenge | 70.5% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: science | 1221 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: medicine and healthcare | 1187 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: legal and government | 1257 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: business and finance | 1224 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1058 | Only Qwen3 235B A22B Instruct 2507 measured |
| Design Arena: UI components | Not measured | 962 | Only Qwen3 235B A22B Instruct 2507 measured |
| Design Arena: game dev | Not measured | 951 | Only Qwen3 235B A22B Instruct 2507 measured |
| Design Arena: data viz | Not measured | 1070 | Only Qwen3 235B A22B Instruct 2507 measured |
| Design Arena: 3D | Not measured | 994 | Only Qwen3 235B A22B Instruct 2507 measured |
| Design Arena: all code categories | Not measured | 1038 | Only Qwen3 235B A22B Instruct 2507 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| IFBench | Not measured | 51.2% | Only Qwen3 235B A22B Instruct 2507 measured |
| Long context reasoning (AA-LCR) | Not measured | 72.0% | Only Qwen3 235B A22B Instruct 2507 measured |
| DTBench | Not measured | 78.4% | Only Qwen3 235B A22B Instruct 2507 measured |
| LMCA | Not measured | 23.5% | Only Qwen3 235B A22B Instruct 2507 measured |
| HellaSwag | 83.0% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| WinoGrande | 80.8% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text | 1230 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: instruction following | 1223 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: creative writing | 1174 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: English | 1248 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: non-English | 1205 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: Chinese | 1222 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: Russian | 1228 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: multi-turn | 1222 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: longer queries | 1251 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: writing and language | 1191 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: entertainment and media | 1150 | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| Neither model has a result on the other 29 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 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 Instruct 2507 costs less
Repository review
50K input + 3K output tokens
Qwen3 235B A22B Instruct 2507 costs less
Agent loop
200K input + 10K output tokens
Qwen3 235B A22B Instruct 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 | Qwen2.5 Coder 32B Instruct | Qwen3 235B A22B Instruct 2507 |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | Open weights |
| Released | November 11, 2024 | July 21, 2025 |
| Context window | 33K | 262K |
| Input $/Mtok | $0.66 | $0.15 |
| Output $/Mtok | $1.00 | $0.75 |
| 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 Qwen2.5 Coder 32B Instruct better than Qwen3 235B A22B Instruct 2507 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen2.5 Coder 32B Instruct for work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Qwen2.5 Coder 32B Instruct or Qwen3 235B A22B Instruct 2507?
Qwen2.5 Coder 32B Instruct costs $0.66 per million input tokens and $1.00 per million output tokens; Qwen3 235B A22B Instruct 2507 costs $0.15 and $0.75. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen2.5 Coder 32B Instruct or Qwen3 235B A22B Instruct 2507?
Qwen3 235B A22B Instruct 2507, with 262K tokens against 33K.
How many benchmarks is the Qwen2.5 Coder 32B Instruct vs Qwen3 235B A22B Instruct 2507 comparison based on?
5 benchmarks have a result for both models as of October 22, 2026. Qwen2.5 Coder 32B Instruct's coding index rests on 0 independent benchmarks and Qwen3 235B A22B Instruct 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.