Model comparison
GPT-5 Pro vs Qwen-14B
GPT-5 Pro is the stronger model overall, scoring 46.2 to 30.8 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. GPT-5 Pro scores higher in 3 categories and Qwen-14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 39.2 to 18.7.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Pro | Qwen-14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 46.2 | 30.8 |
| Released | 2025-10-06 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 272K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $120 | — |
| Results tracked | 12 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-5 Pro: 43.4 (#77), Qwen-14B: 30.6 (#283)
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| WeirdML | 60.4% | — |
| LMArena Coding | — | 1072 |
| AlgoTune | 1.31 | — |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 39.2 (#52), Qwen-14B: 18.7 (#255)
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| Epoch Capabilities Index | 150.26 | 112.8 |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| ARC-AGI-1 | 70.2% | — |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math GPT-5 Pro leads
GPT-5 Pro: 48.0 (#53), Qwen-14B: 28.7 (#224)
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| LMArena Math | — | 1068 |
| FrontierMath Tier 4 (v1) | 14.6% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
GPT-5 Pro: 56.2 (#39), Qwen-14B: —
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| Humanity's Last Exam | 31.6% | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Not comparable
GPT-5 Pro: —, Qwen-14B: 27.7 (#270)
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1042 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
GPT-5 Pro: —, Qwen-14B: 52.6 (#284)
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
GPT-5 Pro: —, Qwen-14B: 31.3 (#276)
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1029 |
Writing & Preference Not comparable
GPT-5 Pro: —, Qwen-14B: 27.8 (#294)
| Benchmark | GPT-5 Pro | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is GPT-5 Pro better than Qwen-14B?
GPT-5 Pro is the stronger model overall, scoring 46.2 to 30.8 on the Noometry Index.
Is GPT-5 Pro or Qwen-14B better for coding?
GPT-5 Pro scores higher on coding benchmarks: 43.4 versus 30.6 in the Noometry coding category.
How many benchmarks do GPT-5 Pro and Qwen-14B share?
1 benchmark has published results for both models. GPT-5 Pro has 12 scored results on Noometry and Qwen-14B has 18.