GPT-5.2-Codex vs Qwen-Plus
Updated October 21, 2026. 0 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
- Coding
- 45.4
- Overall
- 28.5
- Output $/M
- $14.00
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.78
Decision reading
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; Qwen-Plus has none, so the two cannot be ranked on coding.
Qwen-Plus has the edge where output tokens cost 17.9x less, and where the context window is larger, 1M against 400K tokens.
- Shared results
- 0
- GPT-5.2-Codex only
- 22
- Qwen-Plus only
- 28
- Like-for-like categories
- 0 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only GPT-5.2-Codex has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only GPT-5.2-Codex has a AA Intelligence Index result, 28.5.
Directional only
Long documents
Listed context window
Qwen-Plus
Qwen-Plus takes 1M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen-Plus
GPT-5.2-Codex $0.0088, Qwen-Plus $0.0006 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.2-Codex has the number, $0.43.
Directional only
At a glance
- Coding index
- GPT-5.2-Codex 45.4 from 3 benchmarks, Qwen-Plus not benchmarked.
- Widest category
- No category has a result for both models.
- Widest single gap
- No benchmark has a result for both models.
- Output price
- GPT-5.2-Codex $14.00 against Qwen-Plus $0.78 per million output tokens, 17.9x apart.
- Context window
- GPT-5.2-Codex takes 400K tokens, Qwen-Plus 1M.
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.
CodingDirectional onlySix of these boards feed the Vibe Coding Index13 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| SWE-bench Verified | 72.8% | Not measured | Only GPT-5.2-Codex measured |
| SWE-bench Multilingual | 66.3% | Not measured | Only GPT-5.2-Codex measured |
| LMArena WebDev | 1339 | Not measured | Only GPT-5.2-Codex measured |
| LiveCodeBench (Vals AI) | 88.0% | Not measured | Only GPT-5.2-Codex measured |
| SWE-bench Verified (Vals AI) | 72.4% | Not measured | Only GPT-5.2-Codex measured |
| Vibe Code Bench (Vals AI) | 37.9% | Not measured | Only GPT-5.2-Codex measured |
| Terminal-Bench Hard (Artificial Analysis run) | 37.1% | Not measured | Only GPT-5.2-Codex measured |
| Terminal-Bench | 66.5% | Not measured | Only GPT-5.2-Codex measured |
| ALE-Bench | 1299.9 | Not measured | Only GPT-5.2-Codex measured |
| LMArena Text: coding | Not measured | 1328 | Only Qwen-Plus measured |
| LMArena Text: software and IT | Not measured | 1343 | Only Qwen-Plus measured |
| LMArena WebDev: React | 1329 | Not measured | Only GPT-5.2-Codex measured |
| LMArena WebDev: HTML | 1348 | Not measured | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| AA Intelligence Index | 28.5 | Not measured | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1051 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building full-stack apps | 993 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building mobile apps | 1089 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building Android apps | 1176 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GPT-5.2-Codex measured |
| τ²-Bench Telecom | 92.1% | Not measured | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 89.9% | Not measured | Only GPT-5.2-Codex measured |
| Humanity's Last Exam (Artificial Analysis run) | 35.7% | Not measured | Only GPT-5.2-Codex measured |
| GPQA Diamond (Epoch AI run) | Not measured | 48.1% | Only Qwen-Plus measured |
| LMArena Text: hard prompts | Not measured | 1317 | Only Qwen-Plus measured |
| LMArena Text: expert | Not measured | 1328 | Only Qwen-Plus measured |
| LMArena Text: hard prompts in English | Not measured | 1333 | Only Qwen-Plus measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 17.8% | Only Qwen-Plus measured |
| MATH level 5 | Not measured | 65.3% | Only Qwen-Plus measured |
| LMArena Text: math | Not measured | 1326 | Only Qwen-Plus measured |
| LMArena Text: mathematical work | Not measured | 1332 | Only Qwen-Plus measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| LMArena Text: science | Not measured | 1352 | Only Qwen-Plus measured |
| LMArena Text: medicine and healthcare | Not measured | 1350 | Only Qwen-Plus measured |
| LMArena Text: legal and government | Not measured | 1349 | Only Qwen-Plus measured |
| LMArena Text: business and finance | Not measured | 1303 | Only Qwen-Plus measured |
| Neither model has a result on the other 13 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index16 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| IFBench | 77.6% | Not measured | Only GPT-5.2-Codex measured |
| Long context reasoning (AA-LCR) | 82.3% | Not measured | Only GPT-5.2-Codex measured |
| DTBench | Not measured | 81.1% | Only Qwen-Plus measured |
| LMCA | Not measured | 24.0% | Only Qwen-Plus measured |
| LMArena Text | Not measured | 1326 | Only Qwen-Plus measured |
| LMArena Text: instruction following | Not measured | 1303 | Only Qwen-Plus measured |
| LMArena Text: creative writing | Not measured | 1292 | Only Qwen-Plus measured |
| LMArena Text: English | Not measured | 1339 | Only Qwen-Plus measured |
| LMArena Text: non-English | Not measured | 1310 | Only Qwen-Plus measured |
| LMArena Text: Chinese | Not measured | 1347 | Only Qwen-Plus measured |
| LMArena Text: Japanese | Not measured | 1251 | Only Qwen-Plus measured |
| LMArena Text: Russian | Not measured | 1323 | Only Qwen-Plus measured |
| LMArena Text: multi-turn | Not measured | 1336 | Only Qwen-Plus measured |
| LMArena Text: longer queries | Not measured | 1324 | Only Qwen-Plus measured |
| LMArena Text: writing and language | Not measured | 1296 | Only Qwen-Plus measured |
| LMArena Text: entertainment and media | Not measured | 1270 | Only Qwen-Plus measured |
| Neither model has a result on the other 30 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2-Codex | Qwen-Plus | Leader |
|---|---|---|---|
| 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
Qwen-Plus costs less
Repository review
50K input + 3K output tokens
Qwen-Plus costs less
Agent loop
200K input + 10K output tokens
Qwen-Plus 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.
| Specification | OpenAI GPT-5.2-Codex | Qwen-Plus |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | January 14, 2026 | February 1, 2025 |
| Context window | 400K | 1M |
| Input $/Mtok | $1.75 | $0.26 |
| Output $/Mtok | $14.00 | $0.78 |
| Coding index | 45.4 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $0.43 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2-Codex better than Qwen-Plus for coding?
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; Qwen-Plus has none, so the two cannot be ranked on coding. Qwen-Plus has the edge where output tokens cost 17.9x less, and where the context window is larger, 1M against 400K tokens.
Which is cheaper, GPT-5.2-Codex or Qwen-Plus?
GPT-5.2-Codex costs $1.75 per million input tokens and $14.00 per million output tokens; Qwen-Plus costs $0.26 and $0.78. Cost per solved task is known for GPT-5.2-Codex only.
Which has the bigger context window, GPT-5.2-Codex or Qwen-Plus?
Qwen-Plus, with 1M tokens against 400K.
How many benchmarks is the GPT-5.2-Codex vs Qwen-Plus comparison based on?
0 benchmarks have a result for both models as of October 21, 2026. GPT-5.2-Codex's coding index rests on 3 independent benchmarks and Qwen-Plus's on 0. Where only one model has a result, the page says so instead of naming a winner.