o1 vs Qwen2.5 Coder 32B Instruct
o1 leads Qwen2.5 Coder 32B Instruct on the Artificial Analysis Intelligence Index, 15.2 to 6.7, and Qwen2.5 Coder 32B Instruct costs 60.0x less per output token ($1.00 vs $60.00 per million). Updated October 22, 2026; 29 benchmarks have a result for both.
o1 or Qwen2.5 Coder 32B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick o1 for a larger context window (200K against 33K tokens).
- Shared results
- 29
- o1 only
- 40
- Qwen2.5 Coder 32B Instruct only
- 6
- 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
o1
o1 leads, 15.2 against 6.7.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only o1 has a GPQA Diamond result, 73.2%.
Directional only
Math
AIME
No call
Only o1 has a AIME result, 71.5%.
Directional only
Knowledge
MMLU Pro
No call
Only o1 has a MMLU Pro result, 83.5%.
Directional only
Long documents
Listed context window
o1
o1 takes 200K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen2.5 Coder 32B Instruct
o1 $0.045, Qwen2.5 Coder 32B Instruct $0.0012 per turn.
List prices
At a glance
- Coding index
- o1 not benchmarked, Qwen2.5 Coder 32B Instruct not benchmarked.
- Widest category
- Coding, 29.1 points apart on average over 4 shared benchmarks.
- Widest single gap
- Aider polyglot: o1 61.7% against Qwen2.5 Coder 32B Instruct 16.4%, 45.3 points apart on a 0 to 100 scale.
- Output price
- o1 $60.00 against Qwen2.5 Coder 32B Instruct $1.00 per million output tokens, 60.0x apart.
- Context window
- o1 takes 200K tokens, Qwen2.5 Coder 32B Instruct 33K.
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 | o1 | Bars | Qwen2.5 Coder 32B Instruct | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 5 | 0 | ||
| General | 11 | 0 | ||
| All shared boards | 29 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| Aider polyglot | 61.7% | 16.4% | o1 |
| SWE-bench Verified | Not measured | 47.0% | Only Qwen2.5 Coder 32B Instruct measured |
| AA Coding Index | 39.7 | Not measured | Only o1 measured |
| LiveCodeBench (Vals AI) | 50.3% | Not measured | Only o1 measured |
| LiveCodeBench (Artificial Analysis run) | 67.9% | 29.5% | o1 |
| Terminal-Bench Hard (Artificial Analysis run) | 12.9% | Not measured | Only o1 measured |
| WeirdML | 46.1% | Not measured | Only o1 measured |
| LMArena Text: coding | 1367 | 1276 | o1 |
| LMArena Text: software and IT | 1366 | 1261 | o1 |
| SciCode | 4.6% | Not measured | Only o1 measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 15.2 | 6.7 | o1 |
| Epoch Capabilities Index | 141.7 | 119.5 | o1 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 62.6% | Not measured | Only o1 measured |
| METR time horizons | 51.1% | Not measured | Only o1 measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond | 73.2% | Not measured | Only o1 measured |
| MMMU Pro (Vals AI) | 77.4% | Not measured | Only o1 measured |
| GPQA Diamond (Artificial Analysis run) | 74.7% | 41.7% | o1 |
| Humanity's Last Exam (Artificial Analysis run) | 7.0% | 3.5% | o1 |
| GPQA Diamond (Epoch AI run) | 76.8% | Not measured | Only o1 measured |
| ARC-AGI | 30.7% | Not measured | Only o1 measured |
| SimpleBench | 40.1% | Not measured | Only o1 measured |
| Chess puzzles | 10.0% | Not measured | Only o1 measured |
| VPCT | 37.0% | Not measured | Only o1 measured |
| LMArena Text: hard prompts | 1371 | 1251 | o1 |
| LMArena Text: expert | 1361 | 1221 | o1 |
| LMArena Text: hard prompts in English | 1372 | 1269 | o1 |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| AIME | 71.5% | Not measured | Only o1 measured |
| MATH 500 (Vals AI) | 90.4% | Not measured | Only o1 measured |
| MGSM (Vals AI) | 89.3% | Not measured | Only o1 measured |
| OTIS Mock AIME | 73.3% | Not measured | Only o1 measured |
| FrontierMath, tiers 1 to 3 | 14.7% | Not measured | Only o1 measured |
| MATH level 5 | 94.7% | Not measured | Only o1 measured |
| GSM8K | Not measured | 93.0% | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: math | 1388 | 1251 | o1 |
| LMArena Text: mathematical work | 1390 | 1243 | o1 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| MMLU Pro | 83.5% | Not measured | Only o1 measured |
| LegalBench (Vals AI) | 80.4% | Not measured | Only o1 measured |
| TaxEval (Vals AI) | 74.3% | Not measured | Only o1 measured |
| MedQA (Vals AI) | 96.5% | Not measured | Only o1 measured |
| MMLU Pro (Artificial Analysis run) | 84.1% | 63.5% | o1 |
| SimpleQA Verified | 41.1% | Not measured | Only o1 measured |
| MMLU | Not measured | 79.1% | Only Qwen2.5 Coder 32B Instruct measured |
| GeoBench | 80.0% | Not measured | Only o1 measured |
| AI2 Reasoning Challenge | Not measured | 70.5% | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: science | 1369 | 1221 | o1 |
| LMArena Text: medicine and healthcare | 1355 | 1187 | o1 |
| LMArena Text: legal and government | 1368 | 1257 | o1 |
| LMArena Text: business and finance | 1328 | 1224 | o1 |
| Neither model has a result on the other 5 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | o1 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| IFBench | 70.3% | Not measured | Only o1 measured |
| Long context reasoning (AA-LCR) | 65.0% | Not measured | Only o1 measured |
| DTBench | 74.7% | Not measured | Only o1 measured |
| LMCA | 22.3% | Not measured | Only o1 measured |
| Fiction.LiveBench | 83.3% | Not measured | Only o1 measured |
| Creative writing (Lech Mazur) | 70.2% | Not measured | Only o1 measured |
| HellaSwag | Not measured | 83.0% | Only Qwen2.5 Coder 32B Instruct measured |
| WinoGrande | Not measured | 80.8% | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text | 1366 | 1230 | o1 |
| LMArena Text: instruction following | 1367 | 1223 | o1 |
| LMArena Text: creative writing | 1347 | 1174 | o1 |
| LMArena Vision | 1168 | Not measured | Only o1 measured |
| LMArena Text: English | 1372 | 1248 | o1 |
| LMArena Text: non-English | 1358 | 1205 | o1 |
| LMArena Text: Chinese | 1394 | 1222 | o1 |
| LMArena Text: German | 1337 | Not measured | Only o1 measured |
| LMArena Text: Japanese | 1346 | Not measured | Only o1 measured |
| LMArena Text: Korean | 1396 | Not measured | Only o1 measured |
| LMArena Text: French | 1344 | Not measured | Only o1 measured |
| LMArena Text: Spanish | 1345 | Not measured | Only o1 measured |
| LMArena Text: Russian | 1356 | 1228 | o1 |
| LMArena Text: multi-turn | 1355 | 1222 | o1 |
| LMArena Text: longer queries | 1378 | 1251 | o1 |
| LMArena Text: writing and language | 1360 | 1191 | o1 |
| LMArena Text: entertainment and media | 1358 | 1150 | o1 |
| LMArena Vision: English | 1162 | Not measured | Only o1 measured |
| LMArena Vision: Chinese | 1235 | Not measured | Only o1 measured |
| Neither model has a result on the other 19 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | o1 | Qwen2.5 Coder 32B 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
Qwen2.5 Coder 32B Instruct costs less
Repository review
50K input + 3K output tokens
Qwen2.5 Coder 32B Instruct costs less
Agent loop
200K input + 10K output tokens
Qwen2.5 Coder 32B Instruct 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 o1 | Qwen2.5 Coder 32B Instruct |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | December 17, 2024 | November 11, 2024 |
| Context window | 200K | 33K |
| Input $/Mtok | $15.00 | $0.66 |
| Output $/Mtok | $60.00 | $1.00 |
| 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 o1 better than Qwen2.5 Coder 32B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick o1 for a larger context window (200K against 33K tokens).
Which is cheaper, o1 or Qwen2.5 Coder 32B Instruct?
o1 costs $15.00 per million input tokens and $60.00 per million output tokens; Qwen2.5 Coder 32B Instruct costs $0.66 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, o1 or Qwen2.5 Coder 32B Instruct?
o1, with 200K tokens against 33K.
How many benchmarks is the o1 vs Qwen2.5 Coder 32B Instruct comparison based on?
29 benchmarks have a result for both models as of October 22, 2026. o1's coding index rests on 0 independent benchmarks and Qwen2.5 Coder 32B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.