LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-5 Mini vs Qwen3.5 397B A17B

Updated October 21, 2026. 60 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5 Mini Replace Qwen3.5 397B A17B
GPT-5 MiniOpenAI
Coding
59.8
Overall
20.6
Output $/M
$2.00
1
Qwen3.5 397B A17BQwen
Coding
28.6
Overall
21.4
Output $/M
$2.34
59
vs boards won of 60 shared

Decision reading

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 28.6 for Qwen3.5 397B A17B.

Pick Qwen3.5 397B A17B when what matters is SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AGPT-5 MiniOpenAI59.8/1001 independent benchmark$0.08 per solved taskModel BQwen3.5 397B A17BQwen28.6/1001 independent benchmarkNo cost per solved task
Shared results
60
GPT-5 Mini only
38
Qwen3.5 397B A17B only
5
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 Mini 59.8 from 1 benchmark, Qwen3.5 397B A17B 28.6 from 1 benchmark.
Widest category
Agentic work, 24.6 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GPT-5 Mini 71.1% against Qwen3.5 397B A17B 95.6%, 24.6 points apart on a 0 to 100 scale.
Output price
GPT-5 Mini $2.00 against Qwen3.5 397B A17B $2.34 per million output tokens, 1.2x apart.
Context window
GPT-5 Mini takes 400K 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 MiniBarsQwen3.5 397B A17BTies
Coding04
Intelligence02
Agentic work01
Reasoning09
Math13
Knowledge04
Web design07
General029
All shared boards159
CodingLike-for-likeFour of these boards feed the Vibe Coding Index04
Coding benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
SWE-bench Verified59.8%Not measuredOnly GPT-5 Mini measured
SWE-bench Multilingual39.7%Not measuredOnly GPT-5 Mini measured
LMArena WebDevNot measured1400Only Qwen3.5 397B A17B measured
LiveCodeBench (Vals AI)86.6%Not measuredOnly GPT-5 Mini measured
SWE-bench Verified (Vals AI)60.8%Not measuredOnly GPT-5 Mini measured
Vibe Code Bench (Vals AI)14.2%Not measuredOnly GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)83.8%Not measuredOnly GPT-5 Mini measured
SciCode39.0%44.8%Qwen3.5 397B A17B
Terminal-Bench Hard (Artificial Analysis run)33.3%40.9%Qwen3.5 397B A17B
Terminal-Bench34.8%Not measuredOnly GPT-5 Mini measured
WeirdML52.7%Not measuredOnly GPT-5 Mini measured
ALE-BenchNot measured621.9Only Qwen3.5 397B A17B measured
LMArena Text: coding14061464Qwen3.5 397B A17B
LMArena Text: software and IT13941463Qwen3.5 397B A17B
LMArena WebDev: ReactNot measured1388Only Qwen3.5 397B A17B measured
LMArena WebDev: HTMLNot measured1410Only Qwen3.5 397B A17B measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
AA Intelligence Index20.621.4Qwen3.5 397B A17B
Epoch Capabilities Index145.3146.8Qwen3.5 397B A17B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
τ²-Bench Telecom71.1%95.6%Qwen3.5 397B A17B
APEX-AgentsNot measured24.9%Only Qwen3.5 397B A17B measured
Vending-Bench 2-$31Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
Reasoning benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
GPQA Diamond80.3%Not measuredOnly GPT-5 Mini measured
MMMU Pro (Vals AI)78.9%Not measuredOnly GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)82.8%89.3%Qwen3.5 397B A17B
Humanity's Last Exam (Artificial Analysis run)21.5%29.0%Qwen3.5 397B A17B
GPQA Diamond (Epoch AI run)75.0%86.4%Qwen3.5 397B A17B
ARC-AGI54.3%Not measuredOnly GPT-5 Mini measured
ARC-AGI-24.4%Not measuredOnly GPT-5 Mini measured
Chess puzzles24.0%Not measuredOnly GPT-5 Mini measured
Mystery game puzzles10.0%18.0%Qwen3.5 397B A17B
VPCT40.2%Not measuredOnly GPT-5 Mini measured
LMArena Text: hard prompts13801448Qwen3.5 397B A17B
LMArena Text: expert13791462Qwen3.5 397B A17B
LMArena Text: hard prompts in English13831450Qwen3.5 397B A17B
LMArena Vision: diagrams12021277Qwen3.5 397B A17B
LMArena Vision: homework12101292Qwen3.5 397B A17B
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index13
Math benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
AIME91.5%Not measuredOnly GPT-5 Mini measured
MATH 500 (Vals AI)94.8%Not measuredOnly GPT-5 Mini measured
MGSM (Vals AI)92.6%Not measuredOnly GPT-5 Mini measured
AA Math Index90.7Not measuredOnly GPT-5 Mini measured
AIME 2025 (Artificial Analysis run)90.7%Not measuredOnly GPT-5 Mini measured
OTIS Mock AIME86.7%88.9%Qwen3.5 397B A17B
FrontierMath, tiers 1 to 346.7%31.2%GPT-5 Mini
FrontierMath, tier 412.2%Not measuredOnly GPT-5 Mini measured
ProofBench9.0%Not measuredOnly GPT-5 Mini measured
MATH level 597.8%Not measuredOnly GPT-5 Mini measured
LMArena Text: math13781453Qwen3.5 397B A17B
LMArena Text: mathematical work13801454Qwen3.5 397B A17B
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
MMLU Pro82.2%Not measuredOnly GPT-5 Mini measured
LegalBench (Vals AI)81.8%Not measuredOnly GPT-5 Mini measured
CaseLaw (Vals AI)68.5%Not measuredOnly GPT-5 Mini measured
CorpFin (Vals AI)60.2%Not measuredOnly GPT-5 Mini measured
TaxEval (Vals AI)75.2%Not measuredOnly GPT-5 Mini measured
MortgageTax (Vals AI)66.9%Not measuredOnly GPT-5 Mini measured
MedQA (Vals AI)96.1%Not measuredOnly GPT-5 Mini measured
MedCode (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MMLU Pro (Artificial Analysis run)83.7%Not measuredOnly GPT-5 Mini measured
SimpleQA Verified21.6%Not measuredOnly GPT-5 Mini measured
LMArena Text: science13711457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare13801455Qwen3.5 397B A17B
LMArena Text: legal and government13751441Qwen3.5 397B A17B
LMArena Text: business and finance13581435Qwen3.5 397B A17B
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
Design Arena: websites11251191Qwen3.5 397B A17B
Design Arena: UI components11061163Qwen3.5 397B A17B
Design Arena: game dev11301141Qwen3.5 397B A17B
Design Arena: data viz11311175Qwen3.5 397B A17B
Design Arena: 3D10371161Qwen3.5 397B A17B
Design Arena: all code categories11151180Qwen3.5 397B A17B
Design Arena: SVG10911139Qwen3.5 397B A17B
Design Arena: ASCII art1124Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index029
General benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 397B A17BLeader
SAGE (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MedScribe (Vals AI)80.6%Not measuredOnly GPT-5 Mini measured
IFBench75.4%78.8%Qwen3.5 397B A17B
Long context reasoning (AA-LCR)72.3%77.3%Qwen3.5 397B A17B
DTBench80.5%87.5%Qwen3.5 397B A17B
LMCA34.2%37.9%Qwen3.5 397B A17B
Fiction.LiveBench69.4%Not measuredOnly GPT-5 Mini measured
Creative writing (Lech Mazur)83.1%Not measuredOnly GPT-5 Mini measured
LMArena Text13731437Qwen3.5 397B A17B
LMArena Text: instruction following13571424Qwen3.5 397B A17B
LMArena Text: creative writing13251402Qwen3.5 397B A17B
LMArena Vision12021262Qwen3.5 397B A17B
LMArena Text: English13791443Qwen3.5 397B A17B
LMArena Text: non-English13631430Qwen3.5 397B A17B
LMArena Text: Chinese13861498Qwen3.5 397B A17B
LMArena Text: German13661445Qwen3.5 397B A17B
LMArena Text: Japanese13411429Qwen3.5 397B A17B
LMArena Text: Korean13081384Qwen3.5 397B A17B
LMArena Text: French13861462Qwen3.5 397B A17B
LMArena Text: Spanish13541441Qwen3.5 397B A17B
LMArena Text: Russian13621430Qwen3.5 397B A17B
LMArena Text: Polish13781447Qwen3.5 397B A17B
LMArena Text: multi-turn13631446Qwen3.5 397B A17B
LMArena Text: longer queries13551441Qwen3.5 397B A17B
LMArena Text: writing and language13441415Qwen3.5 397B A17B
LMArena Text: entertainment and media13401399Qwen3.5 397B A17B
LMArena Vision: English12161268Qwen3.5 397B A17B
LMArena Vision: Chinese12141314Qwen3.5 397B A17B
LMArena Vision: reading text11991271Qwen3.5 397B A17B
LMArena Vision: humor12051262Qwen3.5 397B A17B
LMArena Vision: captioning12171230Qwen3.5 397B A17B
LMArena Vision: recognizing things12261265Qwen3.5 397B A17B
LMArena Vision: creative writing11811260Qwen3.5 397B A17B
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5 Mini and Qwen3.5 397B A17B
BenchmarkGPT-5 MiniQwen3.5 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 Mini$0.0013Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

GPT-5 Mini$0.018Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5 Mini$0.070Fits in one request
Qwen3.5 397B A17B$0.101Fits in one request

GPT-5 Mini 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 Mini and Qwen3.5 397B A17B
SpecificationOpenAI GPT-5 MiniQwen3.5 397B A17B
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedAugust 7, 2025February 16, 2026
Context window400K262K
Input $/Mtok$0.25$0.39
Output $/Mtok$2.00$2.34
Coding index59.828.6
Independent measurements behind it11
Cost per solved task$0.08Not computable
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 28.6 for Qwen3.5 397B A17B. Pick Qwen3.5 397B A17B when what matters is SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

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

GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for GPT-5 Mini only.

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

GPT-5 Mini, with 400K tokens against 262K.

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

60 benchmarks have a result for both models as of October 21, 2026. GPT-5 Mini's coding index rests on 1 independent benchmark 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