Model comparison
GPT-5.4 mini vs Qwen3.7 Plus
GPT-5.4 mini and Qwen3.7 Plus score almost the same on the Noometry Index (44.8 vs 45.0), so choose on price, context window or the category you care about most.
Last verified . 30 shared benchmarks.
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. GPT-5.4 mini scores higher in 2 categories and Qwen3.7 Plus in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5.4 mini leads 45.0 to 36.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 51.2% for GPT-5.4 mini and 34.4% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Qwen3.7 Plus accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.4 mini | Qwen3.7 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 44.8 | 45.0 |
| Released | 2026-03-17 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.75 | $0.40 |
| Output $ / M tokens | $4.50 | $1.60 |
| Results tracked | 46 | 32 |
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: 45.0 (#67), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | 27% | 10.2% |
| SciCode | 49.9% | 45.5% |
| LMArena Coding | 1438 | 1473 |
| LMArena WebDev | 1397 | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use GPT-5.4 mini leads
GPT-5.4 mini: 29.6 (#74), Qwen3.7 Plus: 21.2 (#130)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
| DeepResearch Bench | 36.3% | — |
Reasoning Qwen3.7 Plus leads
GPT-5.4 mini: 30.3 (#77), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 61.8% | 74.8% |
| CritPt | 10% | 9.1% |
| Chess Puzzles | 24% | 24% |
| LMArena Hard Prompts | 1424 | 1460 |
| Mystery Game Puzzles | 11% | 17% |
| DTBench | 80% | 84% |
| LMCA | 40.8% | 37.6% |
| Epoch Capabilities Index | 148.83 | 147.39 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| Thematic Generalization | 61.7% | — |
| ForecastBench | 57 | — |
Math Qwen3.7 Plus leads
GPT-5.4 mini: 45.4 (#63), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 34.4% |
| OTIS Mock AIME 2024-2025 | 88.9% | 93.3% |
| LMArena Math | 1418 | 1467 |
| FrontierMath Tier 4 | 9.8% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.7 Plus leads
GPT-5.4 mini: 51.4 (#62), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 86.9% | 87.9% |
| LMArena Expert | 1434 | 1467 |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Qwen3.7 Plus leads
GPT-5.4 mini: 39.0 (#51), Qwen3.7 Plus: 41.2 (#30)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1245 | 1281 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
GPT-5.4 mini: 52.1 (#94), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1405 | 1445 |
| LMArena Chinese | 1446 | 1510 |
| LMArena French | 1440 | 1471 |
| LMArena German | 1407 | 1471 |
| LMArena Japanese | 1375 | 1411 |
| LMArena Korean | 1369 | 1416 |
| LMArena Russian | 1417 | 1457 |
| LMArena Spanish | 1403 | 1453 |
Instruction Following Qwen3.7 Plus leads
GPT-5.4 mini: 74.3 (#99), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1405 | 1439 |
Long Context Qwen3.7 Plus leads
GPT-5.4 mini: 42.9 (#107), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1407 | 1454 |
Writing & Preference Too close to call
GPT-5.4 mini: 64.2 (#56), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | GPT-5.4 mini | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1411 | 1454 |
| LMArena Creative Writing | 1370 | 1439 |
| LMArena Multi-Turn | 1429 | 1459 |
| EQ-Bench Creative Writing | 1665 | — |
Frequently asked questions
Is GPT-5.4 mini better than Qwen3.7 Plus?
GPT-5.4 mini and Qwen3.7 Plus score almost the same on the Noometry Index (44.8 vs 45.0), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5.4 mini or Qwen3.7 Plus?
Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Qwen3.7 Plus better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 400K.
How many benchmarks do GPT-5.4 mini and Qwen3.7 Plus share?
30 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen3.7 Plus has 32.