o1 vs Qwen3.5-9B
o1 leads Qwen3.5-9B on the Artificial Analysis Intelligence Index, 15.2 to 13.3, and Qwen3.5-9B costs 400.0x less per output token ($0.15 vs $60.00 per million). Updated October 21, 2026; 13 benchmarks have a result for both.
o1 or Qwen3.5-9B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick o1 for work measured by Terminal-Bench Hard (Artificial Analysis run) or τ²-Bench Telecom, where it leads.
- Shared results
- 13
- o1 only
- 56
- Qwen3.5-9B only
- 2
- 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 13.3.
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
Qwen3.5-9B
Qwen3.5-9B takes 262K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5-9B
o1 $0.045, Qwen3.5-9B $0.0002 per turn.
List prices
At a glance
- Coding index
- o1 not benchmarked, Qwen3.5-9B not benchmarked.
- Widest category
- Agentic work, 24.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: o1 62.6% against Qwen3.5-9B 86.8%, 24.3 points apart on a 0 to 100 scale.
- Output price
- o1 $60.00 against Qwen3.5-9B $0.15 per million output tokens, 400.0x apart.
- Context window
- o1 takes 200K tokens, Qwen3.5-9B 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 | o1 | Bars | Qwen3.5-9B | Ties |
|---|---|---|---|---|
| Coding | 1 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 3 | ||
| Math | 1 | 0 | ||
| General | 2 | 2 | ||
| All shared boards | 6 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index11
| Benchmark | o1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| Aider polyglot | 61.7% | Not measured | Only o1 measured |
| AA Coding Index | 39.7 | 23.5 | o1 |
| LiveCodeBench (Vals AI) | 50.3% | Not measured | Only o1 measured |
| LiveCodeBench (Artificial Analysis run) | 67.9% | Not measured | Only o1 measured |
| SciCode | Not measured | 29.5% | Only Qwen3.5-9B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 12.9% | 24.2% | Qwen3.5-9B |
| Terminal-Bench | Not measured | 9.2% | Only Qwen3.5-9B measured |
| WeirdML | 46.1% | Not measured | Only o1 measured |
| LMArena Text: coding | 1367 | Not measured | Only o1 measured |
| LMArena Text: software and IT | 1366 | Not measured | Only o1 measured |
| SciCode | 4.6% | Not measured | Only o1 measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | o1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| AA Intelligence Index | 15.2 | 13.3 | o1 |
| Epoch Capabilities Index | 141.7 | 139.3 | o1 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | o1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 62.6% | 86.8% | Qwen3.5-9B |
| 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 index03
| Benchmark | o1 | Qwen3.5-9B | 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% | 80.6% | Qwen3.5-9B |
| Humanity's Last Exam (Artificial Analysis run) | 7.0% | 14.9% | Qwen3.5-9B |
| GPQA Diamond (Epoch AI run) | 76.8% | 79.0% | Qwen3.5-9B |
| 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 | Not measured | Only o1 measured |
| LMArena Text: expert | 1361 | Not measured | Only o1 measured |
| LMArena Text: hard prompts in English | 1372 | Not measured | Only o1 measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | o1 | Qwen3.5-9B | 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% | 61.7% | o1 |
| FrontierMath, tiers 1 to 3 | 14.7% | Not measured | Only o1 measured |
| MATH level 5 | 94.7% | Not measured | Only o1 measured |
| LMArena Text: math | 1388 | Not measured | Only o1 measured |
| LMArena Text: mathematical work | 1390 | Not measured | Only o1 measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | o1 | Qwen3.5-9B | 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% | Not measured | Only o1 measured |
| SimpleQA Verified | 41.1% | Not measured | Only o1 measured |
| GeoBench | 80.0% | Not measured | Only o1 measured |
| LMArena Text: science | 1369 | Not measured | Only o1 measured |
| LMArena Text: medicine and healthcare | 1355 | Not measured | Only o1 measured |
| LMArena Text: legal and government | 1368 | Not measured | Only o1 measured |
| LMArena Text: business and finance | 1328 | Not measured | Only o1 measured |
| Neither model has a result on the other 7 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | o1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | o1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| IFBench | 70.3% | 66.7% | o1 |
| Long context reasoning (AA-LCR) | 65.0% | 70.0% | Qwen3.5-9B |
| DTBench | 74.7% | 71.2% | o1 |
| LMCA | 22.3% | 24.5% | Qwen3.5-9B |
| Fiction.LiveBench | 83.3% | Not measured | Only o1 measured |
| Creative writing (Lech Mazur) | 70.2% | Not measured | Only o1 measured |
| LMArena Text | 1366 | Not measured | Only o1 measured |
| LMArena Text: instruction following | 1367 | Not measured | Only o1 measured |
| LMArena Text: creative writing | 1347 | Not measured | Only o1 measured |
| LMArena Vision | 1168 | Not measured | Only o1 measured |
| LMArena Text: English | 1372 | Not measured | Only o1 measured |
| LMArena Text: non-English | 1358 | Not measured | Only o1 measured |
| LMArena Text: Chinese | 1394 | Not measured | Only o1 measured |
| 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 | Not measured | Only o1 measured |
| LMArena Text: multi-turn | 1355 | Not measured | Only o1 measured |
| LMArena Text: longer queries | 1378 | Not measured | Only o1 measured |
| LMArena Text: writing and language | 1360 | Not measured | Only o1 measured |
| LMArena Text: entertainment and media | 1358 | Not measured | Only o1 measured |
| 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 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | o1 | Qwen3.5-9B | 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
Qwen3.5-9B costs less
Repository review
50K input + 3K output tokens
Qwen3.5-9B costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-9B 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 | Qwen3.5-9B |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | December 17, 2024 | March 10, 2026 |
| Context window | 200K | 262K |
| Input $/Mtok | $15.00 | $0.10 |
| Output $/Mtok | $60.00 | $0.15 |
| 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 Qwen3.5-9B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick o1 for work measured by Terminal-Bench Hard (Artificial Analysis run) or τ²-Bench Telecom, where it leads.
Which is cheaper, o1 or Qwen3.5-9B?
o1 costs $15.00 per million input tokens and $60.00 per million output tokens; Qwen3.5-9B costs $0.10 and $0.15. Cost per solved task is known for neither of them.
Which has the bigger context window, o1 or Qwen3.5-9B?
Qwen3.5-9B, with 262K tokens against 200K.
How many benchmarks is the o1 vs Qwen3.5-9B comparison based on?
13 benchmarks have a result for both models as of October 21, 2026. o1's coding index rests on 0 independent benchmarks and Qwen3.5-9B's on 0. Where only one model has a result, the page says so instead of naming a winner.