GPT-5.2 vs Qwen3.5 397B A17B
GPT-5.2 leads Qwen3.5 397B A17B on the Artificial Analysis Intelligence Index, 30.4 to 21.4, and Qwen3.5 397B A17B costs 6.0x less per output token ($2.34 vs $14.00 per million). Updated October 22, 2026; 62 benchmarks have a result for both.
GPT-5.2 or Qwen3.5 397B A17B: which to pick
Only GPT-5.2 has a coding score, 55.9 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding.
Pick Qwen3.5 397B A17B for output tokens 6.0x cheaper ($2.34 vs $14.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 62
- GPT-5.2 only
- 52
- Qwen3.5 397B A17B only
- 3
- 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only GPT-5.2 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.2
GPT-5.2 leads, 30.4 against 21.4.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-5.2 has a GPQA Diamond result, 91.7%.
Directional only
Math
AIME
No call
Only GPT-5.2 has a AIME result, 96.9%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.2 has a MMLU Pro result, 86.2%.
Directional only
Web design
Design Arena: websites
GPT-5.2
GPT-5.2 leads, 1195 against 1190.
Same board, both measured
Long documents
Listed context window
GPT-5.2
GPT-5.2 takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5 397B A17B
GPT-5.2 $0.0088, Qwen3.5 397B A17B $0.0016 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.2 has the number, $1.91.
Directional only
At a glance
- Coding index
- GPT-5.2 55.9 from 3 benchmarks, Qwen3.5 397B A17B not benchmarked.
- Widest category
- Math, 11.9 points apart on average over 4 shared benchmarks.
- Widest single gap
- FrontierMath, tiers 1 to 3: GPT-5.2 67.4% against Qwen3.5 397B A17B 31.2%, 36.2 points apart on a 0 to 100 scale.
- Output price
- GPT-5.2 $14.00 against Qwen3.5 397B A17B $2.34 per million output tokens, 6.0x apart.
- Context window
- GPT-5.2 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.
| Category | GPT-5.2 | Bars | Qwen3.5 397B A17B | Ties |
|---|---|---|---|---|
| Coding | 4 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 4 | 5 | ||
| Math | 2 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 4 | 2 | 1 tie | |
| General | 4 | 25 | ||
| All shared boards | 20 | 41 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index42
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| SWE-bench Verified | 72.8% | Not measured | Only GPT-5.2 measured |
| SWE-bench Multilingual | 66.7% | Not measured | Only GPT-5.2 measured |
| LMArena WebDev | 1417 | 1400 | GPT-5.2 |
| LiveCodeBench (Vals AI) | 85.4% | Not measured | Only GPT-5.2 measured |
| SWE-bench Verified (Vals AI) | 75.8% | Not measured | Only GPT-5.2 measured |
| Vibe Code Bench (Vals AI) | 53.5% | Not measured | Only GPT-5.2 measured |
| LiveCodeBench (Artificial Analysis run) | 89.4% | Not measured | Only GPT-5.2 measured |
| SciCode | Not measured | 44.8% | Only Qwen3.5 397B A17B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 40.9% | GPT-5.2 |
| Terminal-Bench | 64.9% | Not measured | Only GPT-5.2 measured |
| GSO-Bench | 27.5% | Not measured | Only GPT-5.2 measured |
| WeirdML | 72.2% | Not measured | Only GPT-5.2 measured |
| ALE-Bench | 1293.5 | 621.9 | GPT-5.2 |
| LMArena Text: coding | 1442 | 1464 | Qwen3.5 397B A17B |
| LMArena Text: software and IT | 1434 | 1463 | Qwen3.5 397B A17B |
| LMArena WebDev: React | Not measured | 1388 | Only Qwen3.5 397B A17B measured |
| LMArena WebDev: HTML | 1427 | 1410 | GPT-5.2 |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 21.4 | GPT-5.2 |
| Epoch Capabilities Index | 153.7 | 146.8 | GPT-5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1086 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building full-stack apps | 1043 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building mobile apps | 1093 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Android apps | 1059 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GPT-5.2 measured |
| τ²-Bench Telecom | 84.8% | 95.6% | Qwen3.5 397B A17B |
| APEX-Agents | Not measured | 24.9% | Only Qwen3.5 397B A17B measured |
| METR time horizons | 75.3% | Not measured | Only GPT-5.2 measured |
| Remote Labor Index | 2.5% | Not measured | Only GPT-5.2 measured |
| GDPval | 49.7% | Not measured | Only GPT-5.2 measured |
| DeepResearch Bench | 41.1% | Not measured | Only GPT-5.2 measured |
| Vending-Bench 2 | $3,591 | Not measured | Only GPT-5.2 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 55.9% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index45
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | Not measured | Only GPT-5.2 measured |
| MMMU Pro (Vals AI) | 86.7% | Not measured | Only GPT-5.2 measured |
| GPQA Diamond (Artificial Analysis run) | 90.3% | 89.3% | GPT-5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 37.7% | 29.0% | GPT-5.2 |
| GPQA Diamond (Epoch AI run) | 91.4% | 86.4% | GPT-5.2 |
| ARC-AGI | 86.2% | Not measured | Only GPT-5.2 measured |
| ARC-AGI-2 | 52.9% | Not measured | Only GPT-5.2 measured |
| SimpleBench | 45.8% | Not measured | Only GPT-5.2 measured |
| Chess puzzles | 48.0% | Not measured | Only GPT-5.2 measured |
| Mystery game puzzles | 23.0% | 18.0% | GPT-5.2 |
| EBR-bench | 23.0% | Not measured | Only GPT-5.2 measured |
| VPCT | 84.0% | Not measured | Only GPT-5.2 measured |
| LMArena Text: hard prompts | 1428 | 1448 | Qwen3.5 397B A17B |
| LMArena Text: expert | 1445 | 1462 | Qwen3.5 397B A17B |
| LMArena Text: hard prompts in English | 1431 | 1450 | Qwen3.5 397B A17B |
| LMArena Vision: diagrams | 1265 | 1277 | Qwen3.5 397B A17B |
| LMArena Vision: homework | 1276 | 1292 | Qwen3.5 397B A17B |
| Kagi LLM Benchmark | 73.3% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| AIME | 96.9% | Not measured | Only GPT-5.2 measured |
| MGSM (Vals AI) | 94.0% | Not measured | Only GPT-5.2 measured |
| AA Math Index | 99.0 | Not measured | Only GPT-5.2 measured |
| AIME 2025 (Artificial Analysis run) | 99.0% | Not measured | Only GPT-5.2 measured |
| OTIS Mock AIME | 96.1% | 88.9% | GPT-5.2 |
| FrontierMath, tiers 1 to 3 | 67.4% | 31.2% | GPT-5.2 |
| FrontierMath, tier 4 | 31.7% | Not measured | Only GPT-5.2 measured |
| ProofBench | 15.0% | Not measured | Only GPT-5.2 measured |
| LMArena Text: math | 1440 | 1453 | Qwen3.5 397B A17B |
| LMArena Text: mathematical work | 1442 | 1454 | Qwen3.5 397B A17B |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | Not measured | Only GPT-5.2 measured |
| LegalBench (Vals AI) | 82.8% | Not measured | Only GPT-5.2 measured |
| CaseLaw (Vals AI) | 66.0% | Not measured | Only GPT-5.2 measured |
| CorpFin (Vals AI) | 65.9% | Not measured | Only GPT-5.2 measured |
| TaxEval (Vals AI) | 75.8% | Not measured | Only GPT-5.2 measured |
| MortgageTax (Vals AI) | 67.1% | Not measured | Only GPT-5.2 measured |
| MedQA (Vals AI) | 94.1% | Not measured | Only GPT-5.2 measured |
| MedCode (Vals AI) | 49.8% | Not measured | Only GPT-5.2 measured |
| MMLU Pro (Artificial Analysis run) | 87.4% | Not measured | Only GPT-5.2 measured |
| SimpleQA Verified | 37.1% | Not measured | Only GPT-5.2 measured |
| LMArena Text: science | 1425 | 1457 | Qwen3.5 397B A17B |
| LMArena Text: medicine and healthcare | 1425 | 1455 | Qwen3.5 397B A17B |
| LMArena Text: legal and government | 1427 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: business and finance | 1414 | 1435 | Qwen3.5 397B A17B |
| FACTS Benchmark Suite | 48.5% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| Design Arena: websites | 1195 | 1190 | GPT-5.2 |
| Design Arena: UI components | 1190 | 1160 | GPT-5.2 |
| Design Arena: game dev | 1195 | 1140 | GPT-5.2 |
| Design Arena: data viz | 1202 | 1175 | GPT-5.2 |
| Design Arena: 3D | 1079 | 1160 | Qwen3.5 397B A17B |
| Design Arena: all code categories | 1170 | 1179 | Qwen3.5 397B A17B |
| Design Arena: SVG | 1139 | 1139 | Tie |
| Design Arena: ASCII art | 1152 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index425
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.3% | Not measured | Only GPT-5.2 measured |
| MedScribe (Vals AI) | 84.4% | Not measured | Only GPT-5.2 measured |
| IFBench | 75.4% | 78.8% | Qwen3.5 397B A17B |
| Long context reasoning (AA-LCR) | 82.7% | 77.3% | GPT-5.2 |
| DTBench | 90.9% | 87.5% | GPT-5.2 |
| LMCA | 43.9% | 37.9% | GPT-5.2 |
| CL-bench | 18.2% | Not measured | Only GPT-5.2 measured |
| Furniture assembly | 38.3% | Not measured | Only GPT-5.2 measured |
| LMArena Text | 1416 | 1437 | Qwen3.5 397B A17B |
| LMArena Text: instruction following | 1409 | 1424 | Qwen3.5 397B A17B |
| LMArena Text: creative writing | 1376 | 1402 | Qwen3.5 397B A17B |
| LMArena Vision | 1246 | 1262 | Qwen3.5 397B A17B |
| LMArena Text: English | 1422 | 1443 | Qwen3.5 397B A17B |
| LMArena Text: non-English | 1405 | 1430 | Qwen3.5 397B A17B |
| LMArena Text: Chinese | 1447 | 1498 | Qwen3.5 397B A17B |
| LMArena Text: German | 1444 | 1445 | Qwen3.5 397B A17B |
| LMArena Text: Japanese | 1420 | 1429 | Qwen3.5 397B A17B |
| LMArena Text: Korean | 1374 | 1384 | Qwen3.5 397B A17B |
| LMArena Text: French | 1454 | 1462 | Qwen3.5 397B A17B |
| LMArena Text: Spanish | 1413 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: Russian | 1415 | 1430 | Qwen3.5 397B A17B |
| LMArena Text: Polish | 1426 | 1447 | Qwen3.5 397B A17B |
| LMArena Text: multi-turn | 1419 | 1446 | Qwen3.5 397B A17B |
| LMArena Text: longer queries | 1413 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: writing and language | 1392 | 1415 | Qwen3.5 397B A17B |
| LMArena Text: entertainment and media | 1378 | 1399 | Qwen3.5 397B A17B |
| LMArena Vision: English | 1243 | 1268 | Qwen3.5 397B A17B |
| LMArena Vision: Chinese | 1305 | 1314 | Qwen3.5 397B A17B |
| LMArena Vision: reading text | 1257 | 1271 | Qwen3.5 397B A17B |
| LMArena Vision: humor | 1227 | 1262 | Qwen3.5 397B A17B |
| LMArena Vision: captioning | 1267 | 1230 | GPT-5.2 |
| LMArena Vision: recognizing things | 1232 | 1265 | Qwen3.5 397B A17B |
| LMArena Vision: creative writing | 1225 | 1260 | Qwen3.5 397B A17B |
| LMArena Document | 1405 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2 | Qwen3.5 397B A17B | 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
Qwen3.5 397B A17B costs less
Repository review
50K input + 3K output tokens
Qwen3.5 397B A17B costs less
Agent loop
200K input + 10K output tokens
Qwen3.5 397B A17B 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 | Qwen3.5 397B A17B |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | December 10, 2025 | February 16, 2026 |
| Context window | 400K | 262K |
| Input $/Mtok | $1.75 | $0.39 |
| Output $/Mtok | $14.00 | $2.34 |
| Coding index | 55.9 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $1.91 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2 better than Qwen3.5 397B A17B for coding?
Only GPT-5.2 has a coding score, 55.9 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding. Pick Qwen3.5 397B A17B for output tokens 6.0x cheaper ($2.34 vs $14.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, GPT-5.2 or Qwen3.5 397B A17B?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for GPT-5.2 only.
Which has the bigger context window, GPT-5.2 or Qwen3.5 397B A17B?
GPT-5.2, with 400K tokens against 262K.
How many benchmarks is the GPT-5.2 vs Qwen3.5 397B A17B comparison based on?
62 benchmarks have a result for both models as of October 22, 2026. GPT-5.2's coding index rests on 3 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.