Enter opens the highlighted result. Esc closes.

GPT-5.1-Codex-Mini vs Qwen3 30B A3B

GPT-5.1-Codex-Mini leads Qwen3 30B A3B on the Artificial Analysis Intelligence Index, 20.4 to 7.6, and Qwen3 30B A3B costs 4.0x less per output token ($0.50 vs $2.00 per million). Updated October 21, 2026; 16 benchmarks have a result for both.

Replace GPT-5.1-Codex-Mini Replace Qwen3 30B A3B
GPT-5.1-Codex-MiniOpenAI
Coding
No data
Overall
No data
Output $/M
$2.00
16
Qwen3 30B A3BQwen
Coding
No data
Overall
38.2
Output $/M
$0.50
0
vs boards won of 16 shared

GPT-5.1-Codex-Mini or Qwen3 30B A3B: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GPT-5.1-Codex-Mini for a larger context window (400K against 41K tokens).

Model AGPT-5.1-Codex-MiniOpenAINot benchmarked1 independent benchmarkNo cost per solved taskModel BQwen3 30B A3BQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
16
GPT-5.1-Codex-Mini only
6
Qwen3 30B A3B only
36
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-5.1-Codex-Mini not benchmarked, Qwen3 30B A3B not benchmarked.
Widest category
General, 46.5 points apart on average over 2 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): GPT-5.1-Codex-Mini 66.7% against Qwen3 30B A3B 0.0%, 66.7 points apart on a 0 to 100 scale.
Output price
GPT-5.1-Codex-Mini $2.00 against Qwen3 30B A3B $0.50 per million output tokens, 4.0x apart.
Context window
GPT-5.1-Codex-Mini takes 400K tokens, Qwen3 30B A3B 41K.

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-5.1-Codex-MiniBarsQwen3 30B A3BTies
Coding20
Intelligence10
Agentic work10
Reasoning20
Math20
Knowledge10
Web design50
General20
All shared boards160
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
LMArena WebDev1244Not measuredOnly GPT-5.1-Codex-Mini measured
LiveCodeBench (Artificial Analysis run)83.6%50.6%GPT-5.1-Codex-Mini
Terminal-Bench Hard (Artificial Analysis run)33.3%6.8%GPT-5.1-Codex-Mini
Terminal-Bench61.6%Not measuredOnly GPT-5.1-Codex-Mini measured
WeirdMLNot measured29.8%Only Qwen3 30B A3B measured
LMArena Text: codingNot measured1337Only Qwen3 30B A3B measured
LMArena Text: software and ITNot measured1340Only Qwen3 30B A3B measured
LMArena WebDev: HTML1253Not measuredOnly GPT-5.1-Codex-Mini measured
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
AA Intelligence Index20.47.6GPT-5.1-Codex-Mini
Epoch Capabilities IndexNot measured137.3Only Qwen3 30B A3B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
τ²-Bench Telecom62.9%26.0%GPT-5.1-Codex-Mini
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
GPQA Diamond (Artificial Analysis run)81.3%61.6%GPT-5.1-Codex-Mini
Humanity's Last Exam (Artificial Analysis run)18.5%6.2%GPT-5.1-Codex-Mini
GPQA Diamond (Epoch AI run)Not measured61.7%Only Qwen3 30B A3B measured
LMArena Text: hard promptsNot measured1314Only Qwen3 30B A3B measured
LMArena Text: expertNot measured1314Only Qwen3 30B A3B measured
LMArena Text: hard prompts in EnglishNot measured1329Only Qwen3 30B A3B measured
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
AA Math Index91.772.3GPT-5.1-Codex-Mini
AIME 2025 (Artificial Analysis run)91.7%72.3%GPT-5.1-Codex-Mini
OTIS Mock AIMENot measured62.8%Only Qwen3 30B A3B measured
LMArena Text: mathNot measured1355Only Qwen3 30B A3B measured
LMArena Text: mathematical workNot measured1363Only Qwen3 30B A3B measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
MMLU Pro (Artificial Analysis run)82.0%77.7%GPT-5.1-Codex-Mini
LMArena Text: scienceNot measured1321Only Qwen3 30B A3B measured
LMArena Text: medicine and healthcareNot measured1318Only Qwen3 30B A3B measured
LMArena Text: legal and governmentNot measured1314Only Qwen3 30B A3B measured
LMArena Text: business and financeNot measured1309Only Qwen3 30B A3B measured
Neither model has a result on the other 13 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index50
Web design benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
Design Arena: websites1111955GPT-5.1-Codex-Mini
Design Arena: UI components1081946GPT-5.1-Codex-Mini
Design Arena: game dev1092899GPT-5.1-Codex-Mini
Design Arena: data viz1097967GPT-5.1-Codex-Mini
Design Arena: 3D988Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: all code categories1094942GPT-5.1-Codex-Mini
Design Arena: SVG978Not measuredOnly GPT-5.1-Codex-Mini measured
Design Arena: ASCII art1105Not measuredOnly GPT-5.1-Codex-Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
General benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
IFBench67.9%41.5%GPT-5.1-Codex-Mini
Long context reasoning (AA-LCR)66.7%0.0%GPT-5.1-Codex-Mini
DTBenchNot measured60.3%Only Qwen3 30B A3B measured
LMCANot measured15.8%Only Qwen3 30B A3B measured
Fiction.LiveBenchNot measured40.6%Only Qwen3 30B A3B measured
Creative writing (Lech Mazur)Not measured75.3%Only Qwen3 30B A3B measured
LMArena TextNot measured1317Only Qwen3 30B A3B measured
LMArena Text: instruction followingNot measured1283Only Qwen3 30B A3B measured
LMArena Text: creative writingNot measured1271Only Qwen3 30B A3B measured
LMArena Text: EnglishNot measured1335Only Qwen3 30B A3B measured
LMArena Text: non-EnglishNot measured1295Only Qwen3 30B A3B measured
LMArena Text: ChineseNot measured1347Only Qwen3 30B A3B measured
LMArena Text: GermanNot measured1307Only Qwen3 30B A3B measured
LMArena Text: JapaneseNot measured1254Only Qwen3 30B A3B measured
LMArena Text: KoreanNot measured1261Only Qwen3 30B A3B measured
LMArena Text: FrenchNot measured1352Only Qwen3 30B A3B measured
LMArena Text: SpanishNot measured1317Only Qwen3 30B A3B measured
LMArena Text: RussianNot measured1291Only Qwen3 30B A3B measured
LMArena Text: PolishNot measured1299Only Qwen3 30B A3B measured
LMArena Text: multi-turnNot measured1307Only Qwen3 30B A3B measured
LMArena Text: longer queriesNot measured1312Only Qwen3 30B A3B measured
LMArena Text: writing and languageNot measured1290Only Qwen3 30B A3B measured
LMArena Text: entertainment and mediaNot measured1258Only Qwen3 30B A3B measured
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.1-Codex-Mini and Qwen3 30B A3B
BenchmarkGPT-5.1-Codex-MiniQwen3 30B A3BLeader
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-5.1-Codex-Mini$0.0013Fits in one request
Qwen3 30B A3B$0.0004Fits in one request

Qwen3 30B A3B costs less

Repository review

50K input + 3K output tokens

GPT-5.1-Codex-Mini$0.018Fits in one request
Qwen3 30B A3B$0.0075Exceeds the context window

Qwen3 30B A3B costs less

Agent loop

200K input + 10K output tokens

GPT-5.1-Codex-Mini$0.070Fits in one request
Qwen3 30B A3B$0.029Exceeds the context window

Qwen3 30B A3B 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-5.1-Codex-Mini and Qwen3 30B A3B
SpecificationOpenAI GPT-5.1-Codex-MiniQwen3 30B A3B
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedNovember 13, 2025April 28, 2025
Context window400K41K
Input $/Mtok$0.25$0.12
Output $/Mtok$2.00$0.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.1-Codex-Mini better than Qwen3 30B A3B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-5.1-Codex-Mini for a larger context window (400K against 41K tokens).

Which is cheaper, GPT-5.1-Codex-Mini or Qwen3 30B A3B?

GPT-5.1-Codex-Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Qwen3 30B A3B costs $0.12 and $0.50. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-5.1-Codex-Mini or Qwen3 30B A3B?

GPT-5.1-Codex-Mini, with 400K tokens against 41K.

How many benchmarks is the GPT-5.1-Codex-Mini vs Qwen3 30B A3B comparison based on?

16 benchmarks have a result for both models as of October 21, 2026. GPT-5.1-Codex-Mini's coding index rests on 1 independent benchmark and Qwen3 30B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next