Model comparison
GPT-5 Mini vs Qwen3.7 Flash
GPT-5 Mini is the stronger model overall, scoring 41.7 to 39.5 on the Noometry Index. Qwen3.7 Flash costs 13× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. GPT-5 Mini scores higher in 1 category and Qwen3.7 Flash in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.3 to 37.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 46.7% for GPT-5 Mini and 19.3% for Qwen3.7 Flash.
- Qwen3.7 Flash is cheaper at $0.03 / $0.13 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- Qwen3.7 Flash accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5 Mini | Qwen3.7 Flash | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.7 | 39.5 |
| Released | 2025-08-07 | 2026-07-15 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.25 | $0.03 |
| Output $ / M tokens | $2 | $0.13 |
| Results tracked | 60 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5 Mini: 40.0 (#134), Qwen3.7 Flash: —
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| LMArena Coding | 1406 | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.0 (#64), Qwen3.7 Flash: —
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning Qwen3.7 Flash leads
GPT-5 Mini: 24.1 (#153), Qwen3.7 Flash: 27.3 (#108)
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| Chess Puzzles | 30% | 23% |
| Mystery Game Puzzles | 10% | 15% |
| Epoch Capabilities Index | 145.51 | 144.62 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 43.8% |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| EnigmaEval | 8.2% | — |
| LMArena Hard Prompts | 1380 | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.3 (#59), Qwen3.7 Flash: 37.3 (#100)
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.7% | 19.3% |
| OTIS Mock AIME 2024-2025 | 86.7% | 86.7% |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| LMArena Math | 1377 | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge Qwen3.7 Flash leads
GPT-5 Mini: 45.5 (#80), Qwen3.7 Flash: 48.9 (#69)
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| GPQA Diamond | 75% | 82.3% |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
| LMArena Expert | 1377 | — |
Multimodal Not comparable
GPT-5 Mini: 35.0 (#80), Qwen3.7 Flash: —
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual Not comparable
GPT-5 Mini: 49.1 (#131), Qwen3.7 Flash: —
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| LMArena Non-English | 1363 | — |
| LMArena Chinese | 1387 | — |
| LMArena French | 1385 | — |
| LMArena German | 1366 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1306 | — |
| LMArena Russian | 1362 | — |
| LMArena Spanish | 1355 | — |
Instruction Following Not comparable
GPT-5 Mini: 76.4 (#43), Qwen3.7 Flash: —
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| IFEval | 92.7% | — |
| LMArena Instruction Following | 1357 | — |
Long Context Not comparable
GPT-5 Mini: 41.9 (#127), Qwen3.7 Flash: —
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| Fiction.LiveBench | 69.4% | — |
| LMArena Longer Query | 1355 | — |
Writing & Preference Not comparable
GPT-5 Mini: 55.4 (#143), Qwen3.7 Flash: —
| Benchmark | GPT-5 Mini | Qwen3.7 Flash |
|---|---|---|
| LMArena Text | 1373 | — |
| LMArena Creative Writing | 1325 | — |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
| LMArena Multi-Turn | 1363 | — |
Frequently asked questions
Is GPT-5 Mini better than Qwen3.7 Flash?
GPT-5 Mini is the stronger model overall, scoring 41.7 to 39.5 on the Noometry Index. Qwen3.7 Flash costs 13× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Mini or Qwen3.7 Flash?
Qwen3.7 Flash is cheaper. It lists at $0.03 per million input tokens and $0.13 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Which has the bigger context window?
Qwen3.7 Flash does, with 1M tokens against 400K.
How many benchmarks do GPT-5 Mini and Qwen3.7 Flash share?
6 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Qwen3.7 Flash has 7.