Model comparison
GPT-4 Turbo vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 30.3 on the Noometry Index.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Qwen3.7 Plus in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 49.3 to 8.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 93.3% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Qwen3.7 Plus accepts more context: 1M tokens versus 128K.
Side by side
| GPT-4 Turbo | Qwen3.7 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 30.3 | 45.0 |
| Released | 2023-11-06 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 131K |
| Input $ / M tokens | $10 | $0.40 |
| Output $ / M tokens | $30 | $1.60 |
| Results tracked | 36 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
GPT-4 Turbo: 33.4 (#247), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1268 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Qwen3.7 Plus: 21.2 (#130)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
| METR Time Horizons | 36.7% | — |
Reasoning Qwen3.7 Plus leads
GPT-4 Turbo: 14.9 (#311), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| Chess Puzzles | 6% | 24% |
| LMArena Hard Prompts | 1251 | 1460 |
| DTBench | 61.6% | 84% |
| LMCA | 9.8% | 37.6% |
| Epoch Capabilities Index | 127.25 | 147.39 |
| SimpleBench | 25.1% | — |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Mystery Game Puzzles | — | 17% |
| ForecastBench | 59.4 | — |
Math Qwen3.7 Plus leads
GPT-4 Turbo: 8.6 (#316), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 34.4% |
| OTIS Mock AIME 2024-2025 | 6.7% | 93.3% |
| LMArena Math | 1272 | 1467 |
| MATH Level 5 | 46.7% | — |
Knowledge Qwen3.7 Plus leads
GPT-4 Turbo: 24.3 (#263), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 46.6% | 87.9% |
| LMArena Expert | 1223 | 1467 |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |
Multimodal Qwen3.7 Plus leads
GPT-4 Turbo: 30.0 (#104), Qwen3.7 Plus: 41.2 (#30)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1090 | 1281 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
GPT-4 Turbo: 40.7 (#211), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1245 | 1445 |
| LMArena Chinese | 1242 | 1510 |
| LMArena French | 1275 | 1471 |
| LMArena German | 1259 | 1471 |
| LMArena Japanese | 1194 | 1411 |
| LMArena Korean | 1187 | 1416 |
| LMArena Russian | 1259 | 1457 |
| LMArena Spanish | 1260 | 1453 |
Instruction Following Qwen3.7 Plus leads
GPT-4 Turbo: 66.0 (#211), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1250 | 1439 |
Long Context Qwen3.7 Plus leads
GPT-4 Turbo: 38.0 (#200), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1254 | 1454 |
Writing & Preference Qwen3.7 Plus leads
GPT-4 Turbo: 47.9 (#201), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | GPT-4 Turbo | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1272 | 1454 |
| LMArena Creative Writing | 1269 | 1439 |
| LMArena Multi-Turn | 1267 | 1459 |
Frequently asked questions
Is GPT-4 Turbo better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 30.3 on the Noometry Index.
Which is cheaper, GPT-4 Turbo 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-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 33.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 128K.
How many benchmarks do GPT-4 Turbo and Qwen3.7 Plus share?
25 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen3.7 Plus has 32.