Qwen2.5 Coder 32B Instruct vs Qwen3 32B
Qwen3 32B leads Qwen2.5 Coder 32B Instruct on the Artificial Analysis Intelligence Index, 7.3 to 6.7, and Qwen3 32B costs 2.5x less per output token ($0.40 vs $1.00 per million). Updated October 22, 2026; 29 benchmarks have a result for both.
Qwen2.5 Coder 32B Instruct or Qwen3 32B: 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 Aider polyglot or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 29
- Qwen2.5 Coder 32B Instruct only
- 6
- Qwen3 32B only
- 16
- 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 32B
Qwen3 32B leads, 7.3 against 6.7.
Same board, both measured
Long documents
Listed context window
Qwen3 32B
Qwen3 32B takes 131K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 32B
Qwen2.5 Coder 32B Instruct $0.0012, Qwen3 32B $0.0003 per turn.
List prices
At a glance
- Coding index
- Qwen2.5 Coder 32B Instruct not benchmarked, Qwen3 32B not benchmarked.
- Widest category
- Math, 27.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- LMArena Text: medicine and healthcare: Qwen2.5 Coder 32B Instruct 1187 against Qwen3 32B 1368, 30.3 points apart on a 0 to 100 scale.
- Output price
- Qwen2.5 Coder 32B Instruct $1.00 against Qwen3 32B $0.40 per million output tokens, 2.5x apart.
- Context window
- Qwen2.5 Coder 32B Instruct takes 33K tokens, Qwen3 32B 131K.
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 32B | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 5 | ||
| General | 0 | 11 | ||
| All shared boards | 0 | 29 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| Aider polyglot | 16.4% | 40.0% | Qwen3 32B |
| SWE-bench Verified | 47.0% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LiveCodeBench (Artificial Analysis run) | 29.5% | 54.6% | Qwen3 32B |
| SciCode | Not measured | 36.0% | Only Qwen3 32B measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 3.0% | Only Qwen3 32B measured |
| LMArena Text: coding | 1276 | 1357 | Qwen3 32B |
| LMArena Text: software and IT | 1261 | 1366 | Qwen3 32B |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 7.3 | Qwen3 32B |
| Epoch Capabilities Index | 119.5 | 138.4 | Qwen3 32B |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 29.8% | Only Qwen3 32B measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 48.7% | Only Qwen3 32B measured |
| BrowseComp-Plus | Not measured | 10.7% | Only Qwen3 32B 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 | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 41.7% | 66.8% | Qwen3 32B |
| Humanity's Last Exam (Artificial Analysis run) | 3.5% | 7.4% | Qwen3 32B |
| GPQA Diamond (Epoch AI run) | Not measured | 65.7% | Only Qwen3 32B measured |
| LMArena Text: hard prompts | 1251 | 1334 | Qwen3 32B |
| LMArena Text: expert | 1221 | 1362 | Qwen3 32B |
| LMArena Text: hard prompts in English | 1269 | 1350 | Qwen3 32B |
| Kagi LLM Benchmark | Not measured | 48.7% | Only Qwen3 32B measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 73.0 | Only Qwen3 32B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 73.0% | Only Qwen3 32B measured |
| OTIS Mock AIME | Not measured | 66.9% | Only Qwen3 32B measured |
| GSM8K | 93.0% | Not measured | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: math | 1251 | 1399 | Qwen3 32B |
| LMArena Text: mathematical work | 1243 | 1420 | Qwen3 32B |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 63.5% | 79.8% | Qwen3 32B |
| 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 | 1372 | Qwen3 32B |
| LMArena Text: medicine and healthcare | 1187 | 1368 | Qwen3 32B |
| LMArena Text: legal and government | 1257 | 1324 | Qwen3 32B |
| LMArena Text: business and finance | 1224 | 1318 | Qwen3 32B |
| Neither model has a result on the other 11 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index011
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | Leader |
|---|---|---|---|
| IFBench | Not measured | 36.3% | Only Qwen3 32B measured |
| Long context reasoning (AA-LCR) | Not measured | 0.0% | Only Qwen3 32B measured |
| DTBench | Not measured | 67.5% | Only Qwen3 32B measured |
| LMCA | Not measured | 17.3% | Only Qwen3 32B measured |
| Fiction.LiveBench | Not measured | 74.2% | Only Qwen3 32B 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 | 1340 | Qwen3 32B |
| LMArena Text: instruction following | 1223 | 1305 | Qwen3 32B |
| LMArena Text: creative writing | 1174 | 1297 | Qwen3 32B |
| LMArena Text: English | 1248 | 1359 | Qwen3 32B |
| LMArena Text: non-English | 1205 | 1317 | Qwen3 32B |
| LMArena Text: Chinese | 1222 | 1357 | Qwen3 32B |
| LMArena Text: German | Not measured | 1341 | Only Qwen3 32B measured |
| LMArena Text: Russian | 1228 | 1311 | Qwen3 32B |
| LMArena Text: multi-turn | 1222 | 1331 | Qwen3 32B |
| LMArena Text: longer queries | 1251 | 1327 | Qwen3 32B |
| LMArena Text: writing and language | 1191 | 1298 | Qwen3 32B |
| LMArena Text: entertainment and media | 1150 | 1279 | Qwen3 32B |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen2.5 Coder 32B Instruct | Qwen3 32B | 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 32B costs less
Repository review
50K input + 3K output tokens
Qwen3 32B costs less
Agent loop
200K input + 10K output tokens
Qwen3 32B 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 32B |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | Open weights |
| Released | November 11, 2024 | April 28, 2025 |
| Context window | 33K | 131K |
| Input $/Mtok | $0.66 | $0.14 |
| Output $/Mtok | $1.00 | $0.40 |
| 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 32B 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 Aider polyglot or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, Qwen2.5 Coder 32B Instruct or Qwen3 32B?
Qwen2.5 Coder 32B Instruct costs $0.66 per million input tokens and $1.00 per million output tokens; Qwen3 32B costs $0.14 and $0.40. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen2.5 Coder 32B Instruct or Qwen3 32B?
Qwen3 32B, with 131K tokens against 33K.
How many benchmarks is the Qwen2.5 Coder 32B Instruct vs Qwen3 32B comparison based on?
29 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 32B's on 0. Where only one model has a result, the page says so instead of naming a winner.