Enter opens the highlighted result. Esc closes.

o1 vs Qwen3.6 27B

Qwen3.6 27B leads o1 on the Artificial Analysis Intelligence Index, 21.4 to 15.2, and Qwen3.6 27B costs 22.2x less per output token ($2.70 vs $60.00 per million). Updated October 21, 2026; 15 benchmarks have a result for both.

Replace o1 Replace Qwen3.6 27B
o1OpenAI
Coding
No data
Overall
15.2
Output $/M
$60.00
2
Qwen3.6 27BQwen
Coding
36.8
Overall
21.4
Output $/M
$2.70
13
vs boards won of 15 shared

o1 or Qwen3.6 27B: which to pick

Only Qwen3.6 27B has a coding score, 36.8 on the Vibe Coding Index; o1 has none, so the two cannot be ranked on coding.

Pick o1 for work measured by TaxEval (Vals AI) or IFBench, where it leads.

Model Ao1OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.6 27BQwen36.8/1002 independent benchmarks$1.30 per solved task
Shared results
15
o1 only
53
Qwen3.6 27B only
9
Like-for-like categories
7 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.

At a glance

Coding index
o1 not benchmarked, Qwen3.6 27B 36.8 from 2 benchmarks.
Widest category
Agentic work, 31.6 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: o1 62.6% against Qwen3.6 27B 94.2%, 31.6 points apart on a 0 to 100 scale.
Output price
o1 $60.00 against Qwen3.6 27B $2.70 per million output tokens, 22.2x apart.
Context window
o1 takes 200K tokens, Qwen3.6 27B 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.

Boards won, where both have a result
Categoryo1BarsQwen3.6 27BTies
Coding02
Intelligence02
Agentic work01
Reasoning03
Math02
Knowledge10
General13
All shared boards213
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
Aider polyglot61.7%Not measuredOnly o1 measured
AA Coding Index39.753.7Qwen3.6 27B
LiveCodeBench (Vals AI)50.3%Not measuredOnly o1 measured
SWE-bench Verified (Vals AI)Not measured70.0%Only Qwen3.6 27B measured
Vibe Code Bench (Vals AI)Not measured11.9%Only Qwen3.6 27B measured
LiveCodeBench (Artificial Analysis run)67.9%Not measuredOnly o1 measured
SciCodeNot measured42.8%Only Qwen3.6 27B measured
Terminal-Bench Hard (Artificial Analysis run)12.9%34.8%Qwen3.6 27B
WeirdML46.1%Not measuredOnly o1 measured
LMArena Text: coding1367Not measuredOnly o1 measured
LMArena Text: software and IT1366Not measuredOnly o1 measured
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
AA Intelligence Index15.221.4Qwen3.6 27B
Epoch Capabilities Index141.7146.2Qwen3.6 27B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
AA Agentic IndexNot measured18.5Only Qwen3.6 27B measured
τ²-Bench Telecom62.6%94.2%Qwen3.6 27B
METR time horizons51.1%Not measuredOnly o1 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
GPQA Diamond73.2%Not measuredOnly o1 measured
MMMU Pro (Vals AI)77.4%Not measuredOnly o1 measured
GPQA Diamond (Artificial Analysis run)74.7%84.2%Qwen3.6 27B
Humanity's Last Exam (Artificial Analysis run)7.0%23.1%Qwen3.6 27B
GPQA Diamond (Epoch AI run)76.8%85.9%Qwen3.6 27B
ARC-AGI30.7%Not measuredOnly o1 measured
SimpleBench40.1%Not measuredOnly o1 measured
Chess puzzles10.0%Not measuredOnly o1 measured
Mystery game puzzlesNot measured7.0%Only Qwen3.6 27B measured
VPCT37.0%Not measuredOnly o1 measured
LMArena Text: hard prompts1371Not measuredOnly o1 measured
LMArena Text: expert1361Not measuredOnly o1 measured
LMArena Text: hard prompts in English1372Not measuredOnly o1 measured
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
AIME71.5%Not measuredOnly o1 measured
MATH 500 (Vals AI)90.4%Not measuredOnly o1 measured
MGSM (Vals AI)89.3%Not measuredOnly o1 measured
OTIS Mock AIME73.3%91.1%Qwen3.6 27B
FrontierMath, tiers 1 to 314.7%35.1%Qwen3.6 27B
MATH level 594.7%Not measuredOnly o1 measured
LMArena Text: math1388Not measuredOnly o1 measured
LMArena Text: mathematical work1390Not measuredOnly o1 measured
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
MMLU Pro83.5%Not measuredOnly o1 measured
LegalBench (Vals AI)80.4%Not measuredOnly o1 measured
CaseLaw (Vals AI)Not measured53.2%Only Qwen3.6 27B measured
CorpFin (Vals AI)Not measured62.3%Only Qwen3.6 27B measured
TaxEval (Vals AI)74.3%71.3%o1
MortgageTax (Vals AI)Not measured68.3%Only Qwen3.6 27B measured
MedQA (Vals AI)96.5%Not measuredOnly o1 measured
MMLU Pro (Artificial Analysis run)84.1%Not measuredOnly o1 measured
SimpleQA Verified41.1%Not measuredOnly o1 measured
GeoBench80.0%Not measuredOnly o1 measured
LMArena Text: science1369Not measuredOnly o1 measured
LMArena Text: medicine and healthcare1355Not measuredOnly o1 measured
LMArena Text: legal and government1368Not measuredOnly o1 measured
LMArena Text: business and finance1328Not measuredOnly o1 measured
Neither model has a result on the other 3 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index13
General benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
SAGE (Vals AI)Not measured45.6%Only Qwen3.6 27B measured
IFBench70.3%67.6%o1
Long context reasoning (AA-LCR)65.0%77.3%Qwen3.6 27B
DTBench74.7%78.1%Qwen3.6 27B
LMCA22.3%34.5%Qwen3.6 27B
Fiction.LiveBench83.3%Not measuredOnly o1 measured
Creative writing (Lech Mazur)70.2%Not measuredOnly o1 measured
LMArena Text1366Not measuredOnly o1 measured
LMArena Text: instruction following1367Not measuredOnly o1 measured
LMArena Text: creative writing1347Not measuredOnly o1 measured
LMArena Vision1168Not measuredOnly o1 measured
LMArena Text: English1372Not measuredOnly o1 measured
LMArena Text: non-English1358Not measuredOnly o1 measured
LMArena Text: Chinese1394Not measuredOnly o1 measured
LMArena Text: German1337Not measuredOnly o1 measured
LMArena Text: Japanese1346Not measuredOnly o1 measured
LMArena Text: Korean1396Not measuredOnly o1 measured
LMArena Text: French1344Not measuredOnly o1 measured
LMArena Text: Spanish1345Not measuredOnly o1 measured
LMArena Text: Russian1356Not measuredOnly o1 measured
LMArena Text: multi-turn1355Not measuredOnly o1 measured
LMArena Text: longer queries1378Not measuredOnly o1 measured
LMArena Text: writing and language1360Not measuredOnly o1 measured
LMArena Text: entertainment and media1358Not measuredOnly o1 measured
LMArena Vision: English1162Not measuredOnly o1 measured
LMArena Vision: Chinese1235Not measuredOnly o1 measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for o1 and Qwen3.6 27B
Benchmarko1Qwen3.6 27BLeader
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

o1$0.045Fits in one request
Qwen3.6 27B$0.0018Fits in one request

Qwen3.6 27B costs less

Repository review

50K input + 3K output tokens

o1$0.930Fits in one request
Qwen3.6 27B$0.031Fits in one request

Qwen3.6 27B costs less

Agent loop

200K input + 10K output tokens

o1$3.60Exceeds the context window
Qwen3.6 27B$0.117Fits in one request

Qwen3.6 27B 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.

Specifications of o1 and Qwen3.6 27B
SpecificationOpenAI o1Qwen3.6 27B
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedDecember 17, 2024April 27, 2026
Context window200K262K
Input $/Mtok$15.00$0.45
Output $/Mtok$60.00$2.70
Coding indexNot benchmarked36.8
Independent measurements behind it02
Cost per solved taskNot computable$1.30
SourceOpenRouter listingOpenRouter listing

Questions

Is o1 better than Qwen3.6 27B for coding?

Only Qwen3.6 27B has a coding score, 36.8 on the Vibe Coding Index; o1 has none, so the two cannot be ranked on coding. Pick o1 for work measured by TaxEval (Vals AI) or IFBench, where it leads.

Which is cheaper, o1 or Qwen3.6 27B?

o1 costs $15.00 per million input tokens and $60.00 per million output tokens; Qwen3.6 27B costs $0.45 and $2.70. Cost per solved task is known for Qwen3.6 27B only.

Which has the bigger context window, o1 or Qwen3.6 27B?

Qwen3.6 27B, with 262K tokens against 200K.

How many benchmarks is the o1 vs Qwen3.6 27B comparison based on?

15 benchmarks have a result for both models as of October 21, 2026. o1's coding index rests on 0 independent benchmarks and Qwen3.6 27B's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next