Enter opens the highlighted result. Esc closes.

GPT-5.3-Codex vs Qwen3 235B A22B Instruct 2507

GPT-5.3-Codex leads Qwen3 235B A22B Instruct 2507 on the Artificial Analysis Intelligence Index, 32.5 to 12.0, and Qwen3 235B A22B Instruct 2507 costs 18.7x less per output token ($0.75 vs $14.00 per million). Updated October 22, 2026; 14 benchmarks have a result for both.

Replace GPT-5.3-Codex Replace Qwen3 235B A22B Instruct 2507
GPT-5.3-CodexOpenAI
Coding
60.0
Overall
No data
Output $/M
$14.00
14
Qwen3 235B A22B Instruct 2507Qwen
Coding
No data
Overall
No data
Output $/M
$0.75
0
vs boards won of 14 shared

GPT-5.3-Codex or Qwen3 235B A22B Instruct 2507: which to pick

Only GPT-5.3-Codex has a coding score, 60.0 on the Vibe Coding Index; Qwen3 235B A22B Instruct 2507 has none, so the two cannot be ranked on coding.

Pick Qwen3 235B A22B Instruct 2507 for output tokens 18.7x cheaper ($0.75 vs $14.00 per million).

Model AGPT-5.3-CodexOpenAI60.0/1003 independent benchmarks$0.59 per solved taskModel BQwen3 235B A22B Instruct 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
14
GPT-5.3-Codex only
20
Qwen3 235B A22B Instruct 2507 only
10
Like-for-like categories
6 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-5.3-Codex 60.0 from 3 benchmarks, Qwen3 235B A22B Instruct 2507 not benchmarked.
Widest category
Coding, 39.2 points apart on average over 2 shared benchmarks.
Widest single gap
WeirdML: GPT-5.3-Codex 79.3% against Qwen3 235B A22B Instruct 2507 38.7%, 40.6 points apart on a 0 to 100 scale.
Output price
GPT-5.3-Codex $14.00 against Qwen3 235B A22B Instruct 2507 $0.75 per million output tokens, 18.7x apart.
Context window
GPT-5.3-Codex takes 400K tokens, Qwen3 235B A22B Instruct 2507 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-5.3-CodexBarsQwen3 235B A22B Instruct 2507Ties
Coding20
Intelligence10
Agentic work10
Reasoning20
Web design60
General20
All shared boards140
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
LMArena WebDev1407Not measuredOnly GPT-5.3-Codex measured
LiveCodeBench (Vals AI)87.3%Not measuredOnly GPT-5.3-Codex measured
SWE-bench Verified (Vals AI)78.0%Not measuredOnly GPT-5.3-Codex measured
Vibe Code Bench (Vals AI)61.8%Not measuredOnly GPT-5.3-Codex measured
IOI (Vals AI)53.8%Not measuredOnly GPT-5.3-Codex measured
LiveCodeBench (Artificial Analysis run)Not measured78.8%Only Qwen3 235B A22B Instruct 2507 measured
SciCodeNot measured41.4%Only Qwen3 235B A22B Instruct 2507 measured
Terminal-Bench Hard (Artificial Analysis run)53.0%15.2%GPT-5.3-Codex
Terminal-Bench78.4%Not measuredOnly GPT-5.3-Codex measured
WeirdML79.3%38.7%GPT-5.3-Codex
ALE-Bench1655.2Not measuredOnly GPT-5.3-Codex measured
LMArena WebDev: React1395Not measuredOnly GPT-5.3-Codex measured
LMArena WebDev: HTML1422Not measuredOnly GPT-5.3-Codex measured
LMArena WebDev: from an image1443Not measuredOnly GPT-5.3-Codex measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
AA Intelligence Index32.512.0GPT-5.3-Codex
Epoch Capabilities Index157.1Not measuredOnly GPT-5.3-Codex measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
Design Arena: agents building web apps1032Not measuredOnly GPT-5.3-Codex measured
Design Arena: agents building full-stack apps983Not measuredOnly GPT-5.3-Codex measured
Design Arena: agents building mobile apps1053Not measuredOnly GPT-5.3-Codex measured
Design Arena: agents building Android apps1084Not measuredOnly GPT-5.3-Codex measured
Design Arena: agents building Godot games1124Not measuredOnly GPT-5.3-Codex measured
τ²-Bench Telecom86.0%53.2%GPT-5.3-Codex
METR time horizons74.5%Not measuredOnly GPT-5.3-Codex measured
Vending-Bench 2$5,940Not measuredOnly GPT-5.3-Codex measured
Berkeley Function Calling Leaderboard (BFCL)Not measured52.1%Only Qwen3 235B A22B Instruct 2507 measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
GPQA Diamond (Artificial Analysis run)91.5%79.0%GPT-5.3-Codex
Humanity's Last Exam (Artificial Analysis run)42.5%15.9%GPT-5.3-Codex
ARC-AGINot measured11.0%Only Qwen3 235B A22B Instruct 2507 measured
ARC-AGI-2Not measured1.3%Only Qwen3 235B A22B Instruct 2507 measured
Neither model has a result on the other 18 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Math benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
AA Math IndexNot measured91.0Only Qwen3 235B A22B Instruct 2507 measured
AIME 2025 (Artificial Analysis run)Not measured91.0%Only Qwen3 235B A22B Instruct 2507 measured
Neither model has a result on the other 11 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Knowledge benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
MMLU Pro (Artificial Analysis run)Not measured84.3%Only Qwen3 235B A22B Instruct 2507 measured
Neither model has a result on the other 17 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
Design Arena: websites11621058GPT-5.3-Codex
Design Arena: UI components1134962GPT-5.3-Codex
Design Arena: game dev1161951GPT-5.3-Codex
Design Arena: data viz11641070GPT-5.3-Codex
Design Arena: 3D1007994GPT-5.3-Codex
Design Arena: all code categories11441038GPT-5.3-Codex
Design Arena: SVG1129Not measuredOnly GPT-5.3-Codex measured
Design Arena: ASCII art1152Not measuredOnly GPT-5.3-Codex 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-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
IFBench75.4%51.2%GPT-5.3-Codex
Long context reasoning (AA-LCR)83.3%72.0%GPT-5.3-Codex
DTBenchNot measured78.4%Only Qwen3 235B A22B Instruct 2507 measured
LMCANot measured23.5%Only Qwen3 235B A22B Instruct 2507 measured
Neither model has a result on the other 42 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.3-Codex and Qwen3 235B A22B Instruct 2507
BenchmarkGPT-5.3-CodexQwen3 235B A22B Instruct 2507Leader
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-5.3-Codex$0.0088Fits in one request
Qwen3 235B A22B Instruct 2507$0.0005Fits in one request

Qwen3 235B A22B Instruct 2507 costs less

Repository review

50K input + 3K output tokens

GPT-5.3-Codex$0.130Fits in one request
Qwen3 235B A22B Instruct 2507$0.0097Fits in one request

Qwen3 235B A22B Instruct 2507 costs less

Agent loop

200K input + 10K output tokens

GPT-5.3-Codex$0.490Fits in one request
Qwen3 235B A22B Instruct 2507$0.037Fits in one request

Qwen3 235B A22B Instruct 2507 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-5.3-Codex and Qwen3 235B A22B Instruct 2507
SpecificationOpenAI GPT-5.3-CodexQwen3 235B A22B Instruct 2507
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedFebruary 24, 2026July 21, 2025
Context window400K262K
Input $/Mtok$1.75$0.15
Output $/Mtok$14.00$0.75
Coding index60.0Not benchmarked
Independent measurements behind it30
Cost per solved task$0.59Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.3-Codex better than Qwen3 235B A22B Instruct 2507 for coding?

Only GPT-5.3-Codex has a coding score, 60.0 on the Vibe Coding Index; Qwen3 235B A22B Instruct 2507 has none, so the two cannot be ranked on coding. Pick Qwen3 235B A22B Instruct 2507 for output tokens 18.7x cheaper ($0.75 vs $14.00 per million).

Which is cheaper, GPT-5.3-Codex or Qwen3 235B A22B Instruct 2507?

GPT-5.3-Codex costs $1.75 per million input tokens and $14.00 per million output tokens; Qwen3 235B A22B Instruct 2507 costs $0.15 and $0.75. Cost per solved task is known for GPT-5.3-Codex only.

Which has the bigger context window, GPT-5.3-Codex or Qwen3 235B A22B Instruct 2507?

GPT-5.3-Codex, with 400K tokens against 262K.

How many benchmarks is the GPT-5.3-Codex vs Qwen3 235B A22B Instruct 2507 comparison based on?

14 benchmarks have a result for both models as of October 22, 2026. GPT-5.3-Codex's coding index rests on 3 independent benchmarks and Qwen3 235B A22B Instruct 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next