LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-5.1-Codex vs Qwen3.5-122B-A10B

Updated October 21, 2026. 9 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5.1-Codex Replace Qwen3.5-122B-A10B
GPT-5.1-CodexOpenAI
Coding
50.5
Overall
23.7
Output $/M
$10.00
4
Qwen3.5-122B-A10BQwen
Coding
22.9
Overall
17.7
Output $/M
$2.08
5
vs boards won of 9 shared

Decision reading

Pick GPT-5.1-Codex for coding: it scores 50.5 on the Vibe Coding Index against 22.9 for Qwen3.5-122B-A10B.

Pick Qwen3.5-122B-A10B when output tokens cost 4.8x less, or when what matters is LMArena WebDev or LMArena WebDev: HTML, where it leads.

Model AGPT-5.1-CodexOpenAI50.5/1002 independent benchmarks$0.892 per solved taskModel BQwen3.5-122B-A10BQwen22.9/1001 independent benchmarkNo cost per solved task
Shared results
9
GPT-5.1-Codex only
17
Qwen3.5-122B-A10B only
42
Like-for-like categories
5 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-5.1-Codex 50.5 from 2 benchmarks, Qwen3.5-122B-A10B 22.9 from 1 benchmark.
Widest category
Agentic work, 10.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GPT-5.1-Codex 83.0% against Qwen3.5-122B-A10B 93.6%, 10.5 points apart on a 0 to 100 scale.
Output price
GPT-5.1-Codex $10.00 against Qwen3.5-122B-A10B $2.08 per million output tokens, 4.8x apart.
Context window
GPT-5.1-Codex takes 400K tokens, Qwen3.5-122B-A10B 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-5.1-CodexBarsQwen3.5-122B-A10BTies
Coding12
Intelligence10
Agentic work01
Reasoning20
General02
All shared boards45
CodingLike-for-likeFour of these boards feed the Vibe Coding Index12
Coding benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
SWE-bench Verified66.0%Not measuredOnly GPT-5.1-Codex measured
LMArena WebDev13371361Qwen3.5-122B-A10B
AA Coding IndexNot measured43.3Only Qwen3.5-122B-A10B measured
LiveCodeBench (Vals AI)85.5%Not measuredOnly GPT-5.1-Codex measured
Vibe Code Bench (Vals AI)13.1%Not measuredOnly GPT-5.1-Codex measured
LiveCodeBench (Artificial Analysis run)84.9%Not measuredOnly GPT-5.1-Codex measured
SciCodeNot measured39.7%Only Qwen3.5-122B-A10B measured
Terminal-Bench Hard (Artificial Analysis run)34.8%31.1%GPT-5.1-Codex
Terminal-Bench57.8%Not measuredOnly GPT-5.1-Codex measured
ALE-Bench1244.9Not measuredOnly GPT-5.1-Codex measured
LMArena Text: codingNot measured1436Only Qwen3.5-122B-A10B measured
LMArena Text: software and ITNot measured1436Only Qwen3.5-122B-A10B measured
LMArena WebDev: ReactNot measured1353Only Qwen3.5-122B-A10B measured
LMArena WebDev: HTML13461351Qwen3.5-122B-A10B
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
AA Intelligence Index23.717.7GPT-5.1-Codex
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
Design Arena: agents building web apps1018Not measuredOnly GPT-5.1-Codex measured
Design Arena: agents building full-stack apps1086Not measuredOnly GPT-5.1-Codex measured
Design Arena: agents building mobile apps1191Not measuredOnly GPT-5.1-Codex measured
τ²-Bench Telecom83.0%93.6%Qwen3.5-122B-A10B
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
GPQA Diamond (Artificial Analysis run)86.0%85.7%GPT-5.1-Codex
Humanity's Last Exam (Artificial Analysis run)25.7%25.2%GPT-5.1-Codex
Mystery game puzzlesNot measured17.0%Only Qwen3.5-122B-A10B measured
LMArena Text: hard promptsNot measured1421Only Qwen3.5-122B-A10B measured
LMArena Text: expertNot measured1431Only Qwen3.5-122B-A10B measured
LMArena Text: hard prompts in EnglishNot measured1431Only Qwen3.5-122B-A10B measured
LMArena Vision: diagramsNot measured1249Only Qwen3.5-122B-A10B measured
LMArena Vision: homeworkNot measured1261Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 13 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
AA Math Index95.7Not measuredOnly GPT-5.1-Codex measured
AIME 2025 (Artificial Analysis run)95.7%Not measuredOnly GPT-5.1-Codex measured
LMArena Text: mathNot measured1431Only Qwen3.5-122B-A10B measured
LMArena Text: mathematical workNot measured1431Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 9 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Knowledge benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
MMLU Pro (Artificial Analysis run)86.0%Not measuredOnly GPT-5.1-Codex measured
LMArena Text: scienceNot measured1432Only Qwen3.5-122B-A10B measured
LMArena Text: medicine and healthcareNot measured1423Only Qwen3.5-122B-A10B measured
LMArena Text: legal and governmentNot measured1422Only Qwen3.5-122B-A10B measured
LMArena Text: business and financeNot measured1414Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 12 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Web design benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
Design Arena: websites1162Not measuredOnly GPT-5.1-Codex measured
Design Arena: UI components1237Not measuredOnly GPT-5.1-Codex measured
Design Arena: game dev1138Not measuredOnly GPT-5.1-Codex measured
Design Arena: data viz1213Not measuredOnly GPT-5.1-Codex measured
Design Arena: all code categories1153Not measuredOnly GPT-5.1-Codex measured
Neither model has a result on the other 4 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
General benchmarks for GPT-5.1-Codex and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
IFBench70.0%75.7%Qwen3.5-122B-A10B
Long context reasoning (AA-LCR)69.3%76.3%Qwen3.5-122B-A10B
DTBenchNot measured84.3%Only Qwen3.5-122B-A10B measured
LMCANot measured32.2%Only Qwen3.5-122B-A10B measured
LMArena TextNot measured1417Only Qwen3.5-122B-A10B measured
LMArena Text: instruction followingNot measured1399Only Qwen3.5-122B-A10B measured
LMArena Text: creative writingNot measured1368Only Qwen3.5-122B-A10B measured
LMArena VisionNot measured1244Only Qwen3.5-122B-A10B measured
LMArena Text: EnglishNot measured1428Only Qwen3.5-122B-A10B measured
LMArena Text: non-EnglishNot measured1401Only Qwen3.5-122B-A10B measured
LMArena Text: ChineseNot measured1463Only Qwen3.5-122B-A10B measured
LMArena Text: GermanNot measured1425Only Qwen3.5-122B-A10B measured
LMArena Text: JapaneseNot measured1367Only Qwen3.5-122B-A10B measured
LMArena Text: KoreanNot measured1353Only Qwen3.5-122B-A10B measured
LMArena Text: FrenchNot measured1443Only Qwen3.5-122B-A10B measured
LMArena Text: SpanishNot measured1425Only Qwen3.5-122B-A10B measured
LMArena Text: RussianNot measured1400Only Qwen3.5-122B-A10B measured
LMArena Text: PolishNot measured1398Only Qwen3.5-122B-A10B measured
LMArena Text: multi-turnNot measured1416Only Qwen3.5-122B-A10B measured
LMArena Text: longer queriesNot measured1410Only Qwen3.5-122B-A10B measured
LMArena Text: writing and languageNot measured1387Only Qwen3.5-122B-A10B measured
LMArena Text: entertainment and mediaNot measured1366Only Qwen3.5-122B-A10B measured
LMArena Vision: EnglishNot measured1249Only Qwen3.5-122B-A10B measured
LMArena Vision: ChineseNot measured1301Only Qwen3.5-122B-A10B measured
LMArena Vision: reading textNot measured1251Only Qwen3.5-122B-A10B measured
LMArena Vision: humorNot measured1243Only Qwen3.5-122B-A10B measured
LMArena Vision: creative writingNot measured1220Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 19 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 and Qwen3.5-122B-A10B
BenchmarkGPT-5.1-CodexQwen3.5-122B-A10BLeader
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$0.0063Fits in one request
Qwen3.5-122B-A10B$0.0013Fits in one request

Qwen3.5-122B-A10B costs less

Repository review

50K input + 3K output tokens

GPT-5.1-Codex$0.092Fits in one request
Qwen3.5-122B-A10B$0.019Fits in one request

Qwen3.5-122B-A10B costs less

Agent loop

200K input + 10K output tokens

GPT-5.1-Codex$0.350Fits in one request
Qwen3.5-122B-A10B$0.073Fits in one request

Qwen3.5-122B-A10B 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 and Qwen3.5-122B-A10B
SpecificationOpenAI GPT-5.1-CodexQwen3.5-122B-A10B
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedNovember 13, 2025February 25, 2026
Context window400K262K
Input $/Mtok$1.25$0.26
Output $/Mtok$10.00$2.08
Coding index50.522.9
Independent measurements behind it21
Cost per solved task$0.892Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.1-Codex better than Qwen3.5-122B-A10B for coding?

Pick GPT-5.1-Codex for coding: it scores 50.5 on the Vibe Coding Index against 22.9 for Qwen3.5-122B-A10B. Pick Qwen3.5-122B-A10B when output tokens cost 4.8x less, or when what matters is LMArena WebDev or LMArena WebDev: HTML, where it leads.

Which is cheaper, GPT-5.1-Codex or Qwen3.5-122B-A10B?

GPT-5.1-Codex costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3.5-122B-A10B costs $0.26 and $2.08. Cost per solved task is known for GPT-5.1-Codex only.

Which has the bigger context window, GPT-5.1-Codex or Qwen3.5-122B-A10B?

GPT-5.1-Codex, with 400K tokens against 262K.

How many benchmarks is the GPT-5.1-Codex vs Qwen3.5-122B-A10B comparison based on?

9 benchmarks have a result for both models as of October 21, 2026. GPT-5.1-Codex's coding index rests on 2 independent benchmarks and Qwen3.5-122B-A10B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next