Model comparison
GPT-5.4 mini vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 45.0 on the Noometry Index.
Last verified . 34 shared benchmarks.
Alibaba (Qwen)Summary
- They share 34 benchmarks with published results for both. GPT-5.4 mini scores higher in 3 categories and Qwen3.6 Plus in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 45.5.
- The biggest single-benchmark swing is SimpleQA Verified: 29.4% for GPT-5.4 mini and 44.1% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Qwen3.6 Plus accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.4 mini | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.0 | 47.5 |
| Released | 2026-03-17 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.75 | $0.50 |
| Output $ / M tokens | $4.50 | $3 |
| Results tracked | 46 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1397 | 1461 |
| SciCode | 49.9% | 40.7% |
| LMArena Coding | 1438 | 1467 |
| ALE-Bench | 1,189 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| FrontierCode | 27% | — |
| WeirdML | 60.3% | — |
Agentic & Tool Use Not comparable
GPT-5.4 mini: 29.9 (#81), Qwen3.6 Plus: —
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 61.8% | 60.3% |
| CritPt | 10% | 2.9% |
| Chess Puzzles | 24% | 17% |
| Thematic Generalization | 61.7% | 59.5% |
| LMArena Hard Prompts | 1424 | 1449 |
| Mystery Game Puzzles | 11% | 12% |
| DTBench | 80% | 81.9% |
| LMCA | 40.8% | 33.1% |
| Epoch Capabilities Index | 148.84 | 147.65 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| ForecastBench | 57 | — |
Math Qwen3.6 Plus leads
GPT-5.4 mini: 45.5 (#75), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 38.2% |
| OTIS Mock AIME 2024-2025 | 88.9% | 93.3% |
| LMArena Math | 1419 | 1450 |
| FrontierMath (Feb 2025 set) | 28.3% | 26.2% |
| FrontierMath Tier 4 (v1) | 2.1% | 8.3% |
| FrontierMath Tier 4 | 9.8% | — |
| ProofBench | 21% | — |
Knowledge Qwen3.6 Plus leads
GPT-5.4 mini: 51.5 (#67), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 86.9% | 88.4% |
| SimpleQA Verified | 29.4% | 44.1% |
| LMArena Expert | 1435 | 1454 |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), Qwen3.6 Plus: —
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual Qwen3.6 Plus leads
GPT-5.4 mini: 51.9 (#96), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1405 | 1424 |
| LMArena Chinese | 1446 | 1477 |
| LMArena French | 1440 | 1455 |
| LMArena German | 1409 | 1452 |
| LMArena Japanese | 1374 | 1389 |
| LMArena Korean | 1368 | 1379 |
| LMArena Russian | 1417 | 1434 |
| LMArena Spanish | 1405 | 1432 |
Instruction Following Too close to call
GPT-5.4 mini: 74.1 (#102), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1405 | 1425 |
Long Context Qwen3.6 Plus leads
GPT-5.4 mini: 43.0 (#112), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1407 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | GPT-5.4 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1412 | 1437 |
| LMArena Creative Writing | 1370 | 1404 |
| LMArena Multi-Turn | 1429 | 1438 |
| EQ-Bench Creative Writing | 1665 | — |
Frequently asked questions
Is GPT-5.4 mini better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 45.0 on the Noometry Index.
Which is cheaper, GPT-5.4 mini 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 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Qwen3.6 Plus better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 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-5.4 mini and Qwen3.6 Plus share?
34 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen3.6 Plus has 37.