Enter opens the highlighted result. Esc closes.

GPT-5.4 vs Qwen3.5 397B A17B

GPT-5.4 leads Qwen3.5 397B A17B on the Artificial Analysis Intelligence Index, 39.0 to 21.4, and Qwen3.5 397B A17B costs 6.4x less per output token ($2.34 vs $15.00 per million). Updated October 22, 2026; 63 benchmarks have a result for both.

Replace GPT-5.4 Replace Qwen3.5 397B A17B
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
58
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.1
Output $/M
$2.34
4
vs boards won of 63 shared, 1 tied

GPT-5.4 or Qwen3.5 397B A17B: which to pick

Only GPT-5.4 has a coding score, 64.4 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 6.4x cheaper ($2.34 vs $15.00 per million) and work measured by τ²-Bench Telecom or Design Arena: 3D, where it leads.

Model AGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
63
GPT-5.4 only
47
Qwen3.5 397B A17B only
2
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-5.4 64.4 from 3 benchmarks, Qwen3.5 397B A17B not benchmarked.
Widest category
Agentic work, 18.0 points apart on average over 2 shared benchmarks.
Widest single gap
FrontierMath, tiers 1 to 3: GPT-5.4 78.6% against Qwen3.5 397B A17B 31.2%, 47.4 points apart on a 0 to 100 scale.
Output price
GPT-5.4 $15.00 against Qwen3.5 397B A17B $2.34 per million output tokens, 6.4x apart.
Context window
GPT-5.4 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-5.4BarsQwen3.5 397B A17BTies
Coding70
Intelligence20
Agentic work11
Reasoning90
Math40
Knowledge40
Web design511 tie
General262
All shared boards5841 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
LMArena WebDev14641400GPT-5.4
AA Coding Index71.1Not measuredOnly GPT-5.4 measured
LiveCodeBench (Vals AI)84.1%Not measuredOnly GPT-5.4 measured
SWE-bench Verified (Vals AI)78.2%Not measuredOnly GPT-5.4 measured
Vibe Code Bench (Vals AI)67.4%Not measuredOnly GPT-5.4 measured
Code migration (Vals AI)35.0%Not measuredOnly GPT-5.4 measured
ProgramBench (Vals AI)0.5%Not measuredOnly GPT-5.4 measured
SkillsBench (Vals AI)51.7%Not measuredOnly GPT-5.4 measured
SciCodeNot measured44.8%Only Qwen3.5 397B A17B measured
Terminal-Bench Hard (Artificial Analysis run)57.6%40.9%GPT-5.4
Terminal-Bench81.8%Not measuredOnly GPT-5.4 measured
GSO-Bench31.4%Not measuredOnly GPT-5.4 measured
WeirdML77.7%Not measuredOnly GPT-5.4 measured
MirrorCode15.6%Not measuredOnly GPT-5.4 measured
ALE-Bench1607.0621.9GPT-5.4
LMArena Text: coding14961464GPT-5.4
LMArena Text: software and IT14911463GPT-5.4
LMArena WebDev: React14541388GPT-5.4
LMArena WebDev: HTML14781410GPT-5.4
LMArena WebDev: from an image1436Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
AA Intelligence Index39.021.4GPT-5.4
Epoch Capabilities Index157.3146.8GPT-5.4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
Design Arena: agents building web apps1059Not measuredOnly GPT-5.4 measured
Design Arena: agents building full-stack apps1017Not measuredOnly GPT-5.4 measured
Design Arena: agents building mobile apps1087Not measuredOnly GPT-5.4 measured
Design Arena: agents building Android apps1031Not measuredOnly GPT-5.4 measured
Design Arena: agents building Godot games1135Not measuredOnly GPT-5.4 measured
τ²-Bench Telecom87.1%95.6%Qwen3.5 397B A17B
APEX-Agents52.4%24.9%GPT-5.4
METR time horizons74.3%Not measuredOnly GPT-5.4 measured
DeepResearch Bench35.1%Not measuredOnly GPT-5.4 measured
PostTrainBench19.0%Not measuredOnly GPT-5.4 measured
Vending-Bench 2$6,144Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
GPQA Diamond91.7%Not measuredOnly GPT-5.4 measured
MMMU Pro (Vals AI)87.5%Not measuredOnly GPT-5.4 measured
GPQA Diamond (Artificial Analysis run)92.0%89.3%GPT-5.4
Humanity's Last Exam (Artificial Analysis run)43.7%29.0%GPT-5.4
GPQA Diamond (Epoch AI run)93.3%86.4%GPT-5.4
ARC-AGI93.7%Not measuredOnly GPT-5.4 measured
ARC-AGI-274.0%Not measuredOnly GPT-5.4 measured
Chess puzzles48.0%Not measuredOnly GPT-5.4 measured
Mystery game puzzles37.0%18.0%GPT-5.4
EBR-bench25.4%Not measuredOnly GPT-5.4 measured
LMArena Text: hard prompts14851448GPT-5.4
LMArena Text: expert15071462GPT-5.4
LMArena Text: hard prompts in English14791450GPT-5.4
LMArena Vision: diagrams13271277GPT-5.4
LMArena Vision: homework13361292GPT-5.4
Kagi LLM Benchmark63.8%Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
AIME96.7%Not measuredOnly GPT-5.4 measured
OTIS Mock AIME97.8%88.9%GPT-5.4
FrontierMath, tiers 1 to 378.6%31.2%GPT-5.4
FrontierMath, tier 449.0%Not measuredOnly GPT-5.4 measured
ProofBench56.0%Not measuredOnly GPT-5.4 measured
LMArena Text: math14881453GPT-5.4
LMArena Text: mathematical work14971454GPT-5.4
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
MMLU Pro87.5%Not measuredOnly GPT-5.4 measured
LegalBench (Vals AI)86.0%Not measuredOnly GPT-5.4 measured
CaseLaw (Vals AI)63.8%Not measuredOnly GPT-5.4 measured
CorpFin (Vals AI)65.3%Not measuredOnly GPT-5.4 measured
TaxEval (Vals AI)74.0%Not measuredOnly GPT-5.4 measured
MortgageTax (Vals AI)68.3%Not measuredOnly GPT-5.4 measured
MedQA (Vals AI)96.1%Not measuredOnly GPT-5.4 measured
MedCode (Vals AI)41.3%Not measuredOnly GPT-5.4 measured
SimpleQA Verified45.1%Not measuredOnly GPT-5.4 measured
LMArena Text: science14791457GPT-5.4
LMArena Text: medicine and healthcare14581455GPT-5.4
LMArena Text: legal and government14861441GPT-5.4
LMArena Text: business and finance14741435GPT-5.4
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index51
Web design benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
Design Arena: websites11981190GPT-5.4
Design Arena: UI components12121160GPT-5.4
Design Arena: game dev11941140GPT-5.4
Design Arena: data viz11961175GPT-5.4
Design Arena: 3D10651160Qwen3.5 397B A17B
Design Arena: all code categories11791179Tie
Design Arena: SVG11411139GPT-5.4
Design Arena: ASCII art1188Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index262
General benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 397B A17BLeader
SAGE (Vals AI)43.3%Not measuredOnly GPT-5.4 measured
MedScribe (Vals AI)77.5%Not measuredOnly GPT-5.4 measured
IFBench73.9%78.8%Qwen3.5 397B A17B
Long context reasoning (AA-LCR)82.0%77.3%GPT-5.4
DTBench94.4%87.5%GPT-5.4
LMCA52.0%37.9%GPT-5.4
CL-bench27.9%Not measuredOnly GPT-5.4 measured
Furniture assembly37.5%Not measuredOnly GPT-5.4 measured
CL-bench Life21.7%Not measuredOnly GPT-5.4 measured
LMArena Text14691437GPT-5.4
LMArena Text: instruction following14691424GPT-5.4
LMArena Text: creative writing14391402GPT-5.4
LMArena Vision13031262GPT-5.4
LMArena Text: English14671443GPT-5.4
LMArena Text: non-English14651430GPT-5.4
LMArena Text: Chinese15201498GPT-5.4
LMArena Text: German14721445GPT-5.4
LMArena Text: Japanese14851429GPT-5.4
LMArena Text: Korean14491384GPT-5.4
LMArena Text: French14931462GPT-5.4
LMArena Text: Spanish14521441GPT-5.4
LMArena Text: Russian14801430GPT-5.4
LMArena Text: Polish14721447GPT-5.4
LMArena Text: multi-turn14821446GPT-5.4
LMArena Text: longer queries14731441GPT-5.4
LMArena Text: writing and language14581415GPT-5.4
LMArena Text: entertainment and media14381399GPT-5.4
LMArena Vision: English13011268GPT-5.4
LMArena Vision: Chinese13541314GPT-5.4
LMArena Vision: reading text13121271GPT-5.4
LMArena Vision: humor12841262GPT-5.4
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing things12511265Qwen3.5 397B A17B
LMArena Vision: creative writing12831260GPT-5.4
LMArena Document1471Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 and Qwen3.5 397B A17B
BenchmarkGPT-5.4Qwen3.5 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-5.4$0.010Fits 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-5.4$0.170Fits 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-5.4$0.650Fits 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-5.4 and Qwen3.5 397B A17B
SpecificationOpenAI GPT-5.4Qwen3.5 397B A17B
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedMarch 5, 2026February 16, 2026
Context window1.05M262K
Input $/Mtok$2.50$0.39
Output $/Mtok$15.00$2.34
Coding index64.4Not benchmarked
Independent measurements behind it31
Cost per solved task$1.02Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 better than Qwen3.5 397B A17B for coding?

Only GPT-5.4 has a coding score, 64.4 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 6.4x cheaper ($2.34 vs $15.00 per million) and work measured by τ²-Bench Telecom or Design Arena: 3D, where it leads.

Which is cheaper, GPT-5.4 or Qwen3.5 397B A17B?

GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for GPT-5.4 only.

Which has the bigger context window, GPT-5.4 or Qwen3.5 397B A17B?

GPT-5.4, with 1.05M tokens against 262K.

How many benchmarks is the GPT-5.4 vs Qwen3.5 397B A17B comparison based on?

63 benchmarks have a result for both models as of October 22, 2026. GPT-5.4's coding index rests on 3 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