Enter opens the highlighted result. Esc closes.

GPT-6.1 Sol vs Qwen3.5 397B A17B

GPT-6.1 Sol leads Qwen3.5 397B A17B on the Artificial Analysis Intelligence Index, 51.8 to 21.4, and Qwen3.5 397B A17B costs 4.3x less per output token ($2.34 vs $10.00 per million). Updated October 22, 2026; 53 benchmarks have a result for both.

Replace GPT-6.1 Sol Replace Qwen3.5 397B A17B
GPT-6.1 SolOpenAI
Coding
82.4
Overall
81.4
Output $/M
$10.00
47
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.1
Output $/M
$2.34
6
vs boards won of 53 shared

GPT-6.1 Sol or Qwen3.5 397B A17B: which to pick

Only GPT-6.1 Sol has a coding score, 82.4 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding.

Pick Qwen3.5 397B A17B for output tokens 4.3x cheaper ($2.34 vs $10.00 per million) and work measured by LMArena Text: science or LMArena Text: medicine and healthcare, where it leads.

Model AGPT-6.1 SolOpenAI82.4/1005 independent benchmarksNo cost per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
53
GPT-6.1 Sol only
50
Qwen3.5 397B A17B only
13
Like-for-like categories
8 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
GPT-6.1 Sol 82.4 from 5 benchmarks, Qwen3.5 397B A17B not benchmarked.
Widest category
Agentic work, 35.1 points apart on average over 1 shared benchmark.
Widest single gap
ALE-Bench: GPT-6.1 Sol 2743.8 against Qwen3.5 397B A17B 621.9, 70.7 points apart on a 0 to 100 scale.
Output price
GPT-6.1 Sol $10.00 against Qwen3.5 397B A17B $2.34 per million output tokens, 4.3x apart.
Context window
GPT-6.1 Sol takes 1.05M tokens, Qwen3.5 397B A17B 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
CategoryGPT-6.1 SolBarsQwen3.5 397B A17BTies
Coding70
Intelligence20
Agentic work10
Reasoning80
Math50
Knowledge22
Web design60
General164
All shared boards476
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
LiveBench coding96.0%Not measuredOnly GPT-6.1 Sol measured
LMArena WebDev17531400GPT-6.1 Sol
Terminal-Bench 4 (Vals AI)55.0%Not measuredOnly GPT-6.1 Sol measured
Vibe Code Bench (Vals AI)88.9%Not measuredOnly GPT-6.1 Sol measured
Code migration (Vals AI)65.1%Not measuredOnly GPT-6.1 Sol measured
ProgramBench (Vals AI)3.0%Not measuredOnly GPT-6.1 Sol measured
IOI (Vals AI)96.9%Not measuredOnly GPT-6.1 Sol measured
SWE-bench Multimodal (Vals AI)43.5%Not measuredOnly GPT-6.1 Sol measured
CyberBench (Vals AI)39.3%Not measuredOnly GPT-6.1 Sol measured
SciCode55.8%44.8%GPT-6.1 Sol
Terminal-Bench Hard (Artificial Analysis run)Not measured40.9%Only Qwen3.5 397B A17B measured
FrontierCode50.2%Not measuredOnly GPT-6.1 Sol measured
ALE-Bench2743.8621.9GPT-6.1 Sol
LMArena Text: coding14781464GPT-6.1 Sol
LMArena Text: software and IT14761463GPT-6.1 Sol
LMArena WebDev: React17541388GPT-6.1 Sol
LMArena WebDev: HTML18001410GPT-6.1 Sol
LMArena WebDev: from an image1702Not measuredOnly GPT-6.1 Sol measured
SciCode9.2%Not measuredOnly GPT-6.1 Sol measured
SWE-Bench Pro V296.1%Not measuredOnly GPT-6.1 Sol measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
AA Intelligence Index51.821.4GPT-6.1 Sol
Epoch Capabilities Index168.4146.8GPT-6.1 Sol
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
Design Arena: agents building web apps1307Not measuredOnly GPT-6.1 Sol measured
Design Arena: agents building mobile apps1224Not measuredOnly GPT-6.1 Sol measured
Design Arena: spreadsheets1270Not measuredOnly GPT-6.1 Sol measured
LiveBench research83.5%Not measuredOnly GPT-6.1 Sol measured
LiveBench browser88.0%Not measuredOnly GPT-6.1 Sol measured
LiveBench long agentic73.0%Not measuredOnly GPT-6.1 Sol measured
SREBench (Vals AI)50.8%Not measuredOnly GPT-6.1 Sol measured
Finance Agent (Vals AI)52.0%Not measuredOnly GPT-6.1 Sol measured
Tax Agent Bench (Vals AI)21.8%Not measuredOnly GPT-6.1 Sol measured
Legal Research Bench (Vals AI)38.5%Not measuredOnly GPT-6.1 Sol measured
Harvey's Legal Agent Benchmark (Vals AI)6.3%Not measuredOnly GPT-6.1 Sol measured
Excel Modeling Benchmark (Vals AI)70.8%Not measuredOnly GPT-6.1 Sol measured
BioMysteryBench (Vals AI)79.6%Not measuredOnly GPT-6.1 Sol measured
Terminal-Bench-Science (Vals AI)52.9%Not measuredOnly GPT-6.1 Sol measured
Vals Science Index59.6%Not measuredOnly GPT-6.1 Sol measured
Robo-bench (Vals AI)28.3%Not measuredOnly GPT-6.1 Sol measured
τ²-Bench TelecomNot measured95.6%Only Qwen3.5 397B A17B measured
APEX-Agents60.0%24.9%GPT-6.1 Sol
SpireClimb24.7%Not measuredOnly GPT-6.1 Sol measured
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
LiveBench reasoning92.6%Not measuredOnly GPT-6.1 Sol measured
MysteryMechanism (Vals AI)46.4%Not measuredOnly GPT-6.1 Sol measured
GPQA Diamond (Artificial Analysis run)Not measured89.3%Only Qwen3.5 397B A17B measured
Humanity's Last Exam (Artificial Analysis run)52.9%29.0%GPT-6.1 Sol
GPQA Diamond (Epoch AI run)95.4%86.4%GPT-6.1 Sol
ARC-AGI98.5%Not measuredOnly GPT-6.1 Sol measured
ARC-AGI-294.2%Not measuredOnly GPT-6.1 Sol measured
Chess puzzles68.0%Not measuredOnly GPT-6.1 Sol measured
Mystery game puzzles80.0%18.0%GPT-6.1 Sol
EBR-bench54.3%Not measuredOnly GPT-6.1 Sol measured
LMArena Text: hard prompts14631448GPT-6.1 Sol
LMArena Text: expert14891462GPT-6.1 Sol
LMArena Text: hard prompts in English14651450GPT-6.1 Sol
LMArena Vision: diagrams13061277GPT-6.1 Sol
LMArena Vision: homework13561292GPT-6.1 Sol
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
OTIS Mock AIME100.0%88.9%GPT-6.1 Sol
FrontierMath, tiers 1 to 393.7%31.2%GPT-6.1 Sol
FrontierMath, tier 4100.0%Not measuredOnly GPT-6.1 Sol measured
ProofBench99.0%Not measuredOnly GPT-6.1 Sol measured
LMArena Text: math14891453GPT-6.1 Sol
LMArena Text: mathematical work15131454GPT-6.1 Sol
MathArena84.0%19.2%GPT-6.1 Sol
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
Knowledge benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
MedCode (Vals AI)48.8%Not measuredOnly GPT-6.1 Sol measured
SimpleQA Verified73.9%Not measuredOnly GPT-6.1 Sol measured
LMArena Text: science14441457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare14331455Qwen3.5 397B A17B
LMArena Text: legal and government14711441GPT-6.1 Sol
LMArena Text: business and finance14451435GPT-6.1 Sol
FACTS Benchmark Suite75.3%Not measuredOnly GPT-6.1 Sol measured
PRBench Finance46.2%Not measuredOnly GPT-6.1 Sol measured
PRBench Legal47.9%Not measuredOnly GPT-6.1 Sol measured
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
Design Arena: websites13211190GPT-6.1 Sol
Design Arena: UI components13231161GPT-6.1 Sol
Design Arena: game dev13931140GPT-6.1 Sol
Design Arena: data viz12861175GPT-6.1 Sol
Design Arena: 3D14581160GPT-6.1 Sol
Design Arena: all code categories13461179GPT-6.1 Sol
Design Arena: SVGNot measured1139Only Qwen3.5 397B A17B measured
LiveBench design82.1%Not measuredOnly GPT-6.1 Sol measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index164
General benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
Vals Index63.9%Not measuredOnly GPT-6.1 Sol measured
LiveBench data analysis82.7%Not measuredOnly GPT-6.1 Sol measured
Public Benefits Bench (Vals AI)59.3%Not measuredOnly GPT-6.1 Sol measured
SAGE (Vals AI)46.5%Not measuredOnly GPT-6.1 Sol measured
MedScribe (Vals AI)86.5%Not measuredOnly GPT-6.1 Sol measured
IFBenchNot measured78.8%Only Qwen3.5 397B A17B measured
Long context reasoning (AA-LCR)84.0%77.3%GPT-6.1 Sol
DTBench96.5%87.5%GPT-6.1 Sol
LMCA62.8%37.9%GPT-6.1 Sol
Furniture assembly80.0%Not measuredOnly GPT-6.1 Sol measured
LMArena Text14431437GPT-6.1 Sol
LMArena Text: instruction following14661424GPT-6.1 Sol
LMArena Text: creative writing14251402GPT-6.1 Sol
LMArena Vision12881262GPT-6.1 Sol
LMArena Text: English14501443GPT-6.1 Sol
LMArena Text: non-English14331430GPT-6.1 Sol
LMArena Text: Chinese14871498Qwen3.5 397B A17B
LMArena Text: GermanNot measured1445Only Qwen3.5 397B A17B measured
LMArena Text: JapaneseNot measured1429Only Qwen3.5 397B A17B measured
LMArena Text: KoreanNot measured1384Only Qwen3.5 397B A17B measured
LMArena Text: French14601462Qwen3.5 397B A17B
LMArena Text: Spanish14391441Qwen3.5 397B A17B
LMArena Text: Russian14571430GPT-6.1 Sol
LMArena Text: PolishNot measured1447Only Qwen3.5 397B A17B measured
LMArena Text: multi-turn14421446Qwen3.5 397B A17B
LMArena Text: longer queries14581441GPT-6.1 Sol
LMArena Text: writing and language14441415GPT-6.1 Sol
LMArena Text: entertainment and media14261399GPT-6.1 Sol
LMArena Vision: English12741268GPT-6.1 Sol
LMArena Vision: ChineseNot measured1314Only Qwen3.5 397B A17B measured
LMArena Vision: reading text12891271GPT-6.1 Sol
LMArena Vision: humorNot measured1262Only Qwen3.5 397B A17B measured
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writing13011260GPT-6.1 Sol
MultiChallenge82.0%Not measuredOnly GPT-6.1 Sol measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-6.1 Sol and Qwen3.5 397B A17B
BenchmarkGPT-6.1 SolQwen3.5 397B A17BLeader
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

GPT-6.1 Sol$0.0070Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

Qwen3.5 397B A17B costs less

Repository review

50K input + 3K output tokens

GPT-6.1 Sol$0.130Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

Qwen3.5 397B A17B costs less

Agent loop

200K input + 10K output tokens

GPT-6.1 Sol$0.500Fits in one request
Qwen3.5 397B A17B$0.101Fits in one request

Qwen3.5 397B A17B 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 GPT-6.1 Sol and Qwen3.5 397B A17B
SpecificationOpenAI GPT-6.1 SolQwen3.5 397B A17B
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedSeptember 29, 2026February 16, 2026
Context window1.05M262K
Input $/Mtok$2.00$0.39
Output $/Mtok$10.00$2.34
Coding index82.4Not benchmarked
Independent measurements behind it51
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-6.1 Sol better than Qwen3.5 397B A17B for coding?

Only GPT-6.1 Sol has a coding score, 82.4 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding. Pick Qwen3.5 397B A17B for output tokens 4.3x cheaper ($2.34 vs $10.00 per million) and work measured by LMArena Text: science or LMArena Text: medicine and healthcare, where it leads.

Which is cheaper, GPT-6.1 Sol or Qwen3.5 397B A17B?

GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-6.1 Sol or Qwen3.5 397B A17B?

GPT-6.1 Sol, with 1.05M tokens against 262K.

How many benchmarks is the GPT-6.1 Sol vs Qwen3.5 397B A17B comparison based on?

53 benchmarks have a result for both models as of October 22, 2026. GPT-6.1 Sol's coding index rests on 5 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next