Model comparison
GPT-5.4 vs Qwen3.6 Plus
GPT-5.4 is the stronger model overall, scoring 59.5 to 47.3 on the Noometry Index. Qwen3.6 Plus costs 5.0× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.
Last verified . 37 shared benchmarks.
Alibaba (Qwen)Summary
- They share 37 benchmarks with published results for both. GPT-5.4 scores higher in 8 categories and Qwen3.6 Plus in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 leads 61.7 to 28.5.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 78.6% for GPT-5.4 and 38.2% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $2.50 / $15 for GPT-5.4.
- GPT-5.4 accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-5.4 | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 59.5 | 47.3 |
| Released | 2026-03-05 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 66K |
| Input $ / M tokens | $2.50 | $0.50 |
| Output $ / M tokens | $15 | $3 |
| Results tracked | 68 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 leads
GPT-5.4: 52.8 (#28), Qwen3.6 Plus: 40.6 (#125)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 76.9% | 57.9% |
| LMArena WebDev | 1465 | 1461 |
| SciCode | 56.6% | 40.7% |
| LMArena Coding | 1497 | 1467 |
| ALE-Bench | 1,607 | 670.15 |
| DeepSWE | 51.8% | — |
| GSO | 31.4% | — |
| WeirdML | 77.7% | — |
| MirrorCode | 15.6% | — |
| AlgoTune | 1.85 | — |
Agentic & Tool Use Not comparable
GPT-5.4: 46.5 (#12), Qwen3.6 Plus: —
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 6,144 | 5,115 |
| Terminal-Bench | 81.8% | — |
| APEX-Agents | 52.4% | — |
| τ²-bench Banking | 39.4% | — |
| DeepResearch Bench | 35.1% | — |
| PostTrainBench | 19% | — |
| GBAEval | 45.1% | — |
| LMArena Search | 1197 | — |
| METR Time Horizons | 74.3% | — |
Reasoning GPT-5.4 leads
GPT-5.4: 61.7 (#17), Qwen3.6 Plus: 28.5 (#89)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 91.3% | 60.3% |
| CritPt | 23.4% | 2.9% |
| Chess Puzzles | 44% | 17% |
| Thematic Generalization | 80% | 59.5% |
| LMArena Hard Prompts | 1485 | 1449 |
| Mystery Game Puzzles | 37% | 12% |
| DTBench | 94.4% | 81.9% |
| LMCA | 52% | 33.1% |
| Epoch Capabilities Index | 156.92 | 147.67 |
| ARC-AGI-2 | 74% | — |
| Kagi LLM Benchmark | 63.8% | — |
| ARC-AGI-1 | 93.7% | — |
| EnigmaEval | 16% | — |
| EBR-Bench | 25.4% | — |
| ForecastBench | 59.5 | — |
Math GPT-5.4 leads
GPT-5.4: 73.3 (#14), Qwen3.6 Plus: 50.6 (#44)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 78.6% | 38.2% |
| OTIS Mock AIME 2024-2025 | 97.8% | 93.3% |
| LMArena Math | 1488 | 1450 |
| FrontierMath (Feb 2025 set) | 47.6% | 26.2% |
| FrontierMath Tier 4 (v1) | 27.1% | 8.3% |
| FrontierMath Tier 4 | 49% | — |
| MathArena Final-Answer Competitions | 83.1% | — |
| ProofBench | 56% | — |
Knowledge GPT-5.4 leads
GPT-5.4: 65.3 (#13), Qwen3.6 Plus: 56.1 (#40)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 93.3% | 88.4% |
| SimpleQA Verified | 45.1% | 44.1% |
| LMArena Expert | 1507 | 1456 |
| Humanity's Last Exam | 36.2% | — |
| Vectara Hallucination Rate | 7% | — |
Multimodal Not comparable
GPT-5.4: 43.8 (#19), Qwen3.6 Plus: —
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1302 | — |
| Blueprint-Bench 2 | 27.1% | — |
| Furniture Assembly | 37.5% | — |
| LMArena Document | 1471 | — |
Multilingual GPT-5.4 leads
GPT-5.4: 56.4 (#22), Qwen3.6 Plus: 53.5 (#66)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1465 | 1424 |
| LMArena Chinese | 1520 | 1478 |
| LMArena French | 1493 | 1454 |
| LMArena German | 1472 | 1451 |
| LMArena Japanese | 1484 | 1389 |
| LMArena Korean | 1449 | 1381 |
| LMArena Russian | 1480 | 1434 |
| LMArena Spanish | 1453 | 1432 |
Instruction Following GPT-5.4 leads
GPT-5.4: 77.3 (#25), Qwen3.6 Plus: 75.2 (#70)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1469 | 1425 |
Long Context GPT-5.4 leads
GPT-5.4: 50.3 (#8), Qwen3.6 Plus: 45.1 (#48)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| CL-bench | 27.9% | 20.3% |
| LMArena Longer Query | 1474 | 1440 |
| CL-bench Life | 21.7% | — |
Writing & Preference GPT-5.4 leads
GPT-5.4: 72.1 (#18), Qwen3.6 Plus: 62.4 (#78)
| Benchmark | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1469 | 1437 |
| LMArena Creative Writing | 1439 | 1405 |
| LMArena Multi-Turn | 1482 | 1438 |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1272 | — |
Frequently asked questions
Is GPT-5.4 better than Qwen3.6 Plus?
GPT-5.4 is the stronger model overall, scoring 59.5 to 47.3 on the Noometry Index. Qwen3.6 Plus costs 5.0× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 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-5.4 lists at $2.50 and $15.
Is GPT-5.4 or Qwen3.6 Plus better for coding?
GPT-5.4 scores higher on coding benchmarks: 52.8 versus 40.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 does, with 1.05M tokens against 1M.
How many benchmarks do GPT-5.4 and Qwen3.6 Plus share?
37 benchmarks have published results for both models. GPT-5.4 has 68 scored results on Noometry and Qwen3.6 Plus has 37.