Model comparison
GPT-5.2 vs Qwen3.6 Plus
GPT-5.2 is the stronger model overall, scoring 54.1 to 47.5 on the Noometry Index. Qwen3.6 Plus costs 4.3× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Alibaba (Qwen)Summary
- They share 34 benchmarks with published results for both. GPT-5.2 scores higher in 6 categories and Qwen3.6 Plus in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 leads 50.2 to 29.3.
- The biggest single-benchmark swing is Chess Puzzles: 49% for GPT-5.2 and 17% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- Qwen3.6 Plus accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.2 | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 54.1 | 47.5 |
| Released | 2025-12-11 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 66K |
| Input $ / M tokens | $1.75 | $0.50 |
| Output $ / M tokens | $14 | $3 |
| Results tracked | 67 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
GPT-5.2: 51.6 (#37), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 73.8% | 57.9% |
| LMArena WebDev | 1416 | 1461 |
| LMArena Coding | 1447 | 1467 |
| ALE-Bench | 1,294 | 670.15 |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 66.7% | — |
| SciCode | — | 40.7% |
| GSO | 27.4% | — |
| WeirdML | 72.2% | — |
| AlgoTune | 2.05 | — |
Agentic & Tool Use Not comparable
GPT-5.2: 40.2 (#24), Qwen3.6 Plus: —
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 3,591 | 5,115 |
| Terminal-Bench | 64.9% | — |
| Berkeley Function Calling Leaderboard | 55.9% | — |
| GDPval | 49.7% | — |
| Remote Labor Index | 2.5% | — |
| τ²-bench Airline | 83% | — |
| τ²-bench Banking | 32.2% | — |
| τ²-bench Retail | 81.6% | — |
| τ²-bench Telecom | 89.7% | — |
| DeepResearch Bench | 41.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 75.3% | — |
Reasoning GPT-5.2 leads
GPT-5.2: 50.2 (#35), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 83.6% | 60.3% |
| Chess Puzzles | 49% | 17% |
| LMArena Hard Prompts | 1445 | 1449 |
| Mystery Game Puzzles | 23% | 12% |
| DTBench | 90.9% | 81.9% |
| LMCA | 43.9% | 33.1% |
| Epoch Capabilities Index | 153.45 | 147.65 |
| ARC-AGI-2 | 52.9% | — |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | 73.3% | — |
| ARC-AGI-1 | 86.2% | — |
| CritPt | — | 2.9% |
| EnigmaEval | 10.4% | — |
| Thematic Generalization | — | 59.5% |
| EBR-Bench | 23% | — |
| ForecastBench | 60.1 | — |
Math GPT-5.2 leads
GPT-5.2: 60.0 (#38), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 38.2% |
| OTIS Mock AIME 2024-2025 | 96.1% | 93.3% |
| LMArena Math | 1440 | 1450 |
| FrontierMath (Feb 2025 set) | 40.7% | 26.2% |
| FrontierMath Tier 4 (v1) | 18.8% | 8.3% |
| FrontierMath Tier 4 | 31.7% | — |
| MathArena Final-Answer Competitions | 72% | — |
| ProofBench | 15% | — |
Knowledge GPT-5.2 leads
GPT-5.2: 59.3 (#32), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 91.4% | 88.4% |
| SimpleQA Verified | 37.1% | 44.1% |
| LMArena Expert | 1445 | 1454 |
| Humanity's Last Exam | 27.8% | — |
| Vectara Hallucination Rate | 8.4% | — |
Multimodal Not comparable
GPT-5.2: 51.3 (#7), Qwen3.6 Plus: —
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1268 | — |
| VPCT | 84% | — |
| Furniture Assembly | 38.3% | — |
| LMArena Document | 1405 | — |
Multilingual Too close to call
GPT-5.2: 53.4 (#67), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1425 | 1424 |
| LMArena Chinese | 1460 | 1477 |
| LMArena French | 1455 | 1455 |
| LMArena German | 1448 | 1452 |
| LMArena Japanese | 1420 | 1389 |
| LMArena Korean | 1392 | 1379 |
| LMArena Russian | 1440 | 1434 |
| LMArena Spanish | 1433 | 1432 |
Instruction Following Too close to call
GPT-5.2: 74.7 (#89), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1417 | 1425 |
Long Context Qwen3.6 Plus leads
GPT-5.2: 44.0 (#78), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| CL-bench | 18.2% | 20.3% |
| LMArena Longer Query | 1428 | 1439 |
Writing & Preference GPT-5.2 leads
GPT-5.2: 66.8 (#32), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | GPT-5.2 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1439 | 1437 |
| LMArena Creative Writing | 1401 | 1404 |
| LMArena Multi-Turn | 1458 | 1438 |
| EQ-Bench Creative Writing | 1703 | — |
Frequently asked questions
Is GPT-5.2 better than Qwen3.6 Plus?
GPT-5.2 is the stronger model overall, scoring 54.1 to 47.5 on the Noometry Index. Qwen3.6 Plus costs 4.3× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 or Qwen3.6 Plus?
Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is GPT-5.2 or Qwen3.6 Plus better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 400K.
How many benchmarks do GPT-5.2 and Qwen3.6 Plus share?
34 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and Qwen3.6 Plus has 37.