Model comparison
GPT-5 Nano vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 5.1× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. GPT-5 Nano scores higher in 1 category and Qwen3.7 Plus in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Plus leads 64.3 to 39.1.
- The biggest single-benchmark swing is LMCA: 7.9% for GPT-5 Nano and 37.6% for Qwen3.7 Plus.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5 Nano | Qwen3.7 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 33.5 | 45.3 |
| Released | 2025-08-07 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.05 | $0.40 |
| Output $ / M tokens | $0.40 | $1.60 |
| Results tracked | 49 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
GPT-5 Nano: 33.6 (#254), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1351 | 1473 |
| FrontierCode | — | 10.2% |
| SWE-bench Verified (bash only) | 34.8% | — |
| SciCode | — | 45.5% |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use GPT-5 Nano leads
GPT-5 Nano: 25.8 (#106), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
GPT-5 Nano: 16.3 (#306), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| Chess Puzzles | 27% | 24% |
| LMArena Hard Prompts | 1328 | 1460 |
| Mystery Game Puzzles | 9% | 17% |
| DTBench | 62.7% | 84% |
| LMCA | 7.9% | 37.6% |
| Epoch Capabilities Index | 139.38 | 147.37 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 9.1% |
| ForecastBench | 59.1 | — |
Math Qwen3.7 Plus leads
GPT-5 Nano: 29.4 (#241), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20% | 34.4% |
| OTIS Mock AIME 2024-2025 | 81.1% | 93.3% |
| LMArena Math | 1317 | 1466 |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.7 Plus leads
GPT-5 Nano: 35.9 (#178), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 69.4% | 87.9% |
| LMArena Expert | 1321 | 1467 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Qwen3.7 Plus leads
GPT-5 Nano: 31.3 (#108), Qwen3.7 Plus: 41.8 (#33)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1159 | 1279 |
| VPCT | 37.2% | — |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
GPT-5 Nano: 45.3 (#172), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1313 | 1445 |
| LMArena Chinese | 1356 | 1510 |
| LMArena German | 1327 | 1471 |
| LMArena Japanese | 1226 | 1413 |
| LMArena Korean | 1269 | 1415 |
| LMArena Russian | 1296 | 1457 |
| LMArena Spanish | 1360 | 1457 |
| LMArena French | — | 1473 |
Instruction Following Too close to call
GPT-5 Nano: 75.0 (#79), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1306 | 1440 |
| IFEval | 93.2% | — |
Long Context Qwen3.7 Plus leads
GPT-5 Nano: 31.3 (#281), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1312 | 1455 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Qwen3.7 Plus leads
GPT-5 Nano: 39.1 (#249), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | GPT-5 Nano | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1320 | 1455 |
| LMArena Creative Writing | 1249 | 1439 |
| LMArena Multi-Turn | 1311 | 1460 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 33.5 on the Noometry Index. GPT-5 Nano costs 5.1× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or Qwen3.7 Plus?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is GPT-5 Nano or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 33.6 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 Nano and Qwen3.7 Plus share?
25 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Qwen3.7 Plus has 32.