Model comparison
GPT-5 Nano vs Qwen-14B
GPT-5 Nano is the stronger model overall, scoring 33.5 to 31.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. GPT-5 Nano scores higher in 4 categories and Qwen-14B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Nano leads 75.0 to 52.4.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Qwen-14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 33.5 | 31.4 |
| Released | 2025-08-07 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 49 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Nano leads
GPT-5 Nano: 33.6 (#254), Qwen-14B: 31.2 (#288)
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Coding | 1351 | 1071 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Qwen-14B: —
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Qwen-14B leads
GPT-5 Nano: 16.3 (#306), Qwen-14B: 19.6 (#257)
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1027 |
| Epoch Capabilities Index | 139.38 | 113.03 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 59.1 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
GPT-5 Nano: 29.4 (#241), Qwen-14B: 31.2 (#227)
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Math | 1317 | 1068 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
GPT-5 Nano: 35.9 (#178), Qwen-14B: —
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| LMArena Expert | 1321 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Qwen-14B: —
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.3 (#172), Qwen-14B: 27.5 (#275)
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1313 | 1041 |
| LMArena Chinese | 1356 | 1077 |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Russian | 1296 | — |
| LMArena Spanish | 1360 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Qwen-14B: 52.4 (#289)
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1306 | 1031 |
| IFEval | 93.2% | — |
Long Context Too close to call
GPT-5 Nano: 31.3 (#281), Qwen-14B: 31.3 (#280)
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1312 | 1028 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5 Nano leads
GPT-5 Nano: 39.1 (#249), Qwen-14B: 27.6 (#299)
| Benchmark | GPT-5 Nano | Qwen-14B |
|---|---|---|
| LMArena Text | 1320 | 1051 |
| LMArena Creative Writing | 1249 | 1028 |
| LMArena Multi-Turn | 1311 | 1022 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Qwen-14B?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 31.4 on the Noometry Index.
Is GPT-5 Nano or Qwen-14B better for coding?
GPT-5 Nano scores higher on coding benchmarks: 33.6 versus 31.2 in the Noometry coding category.
How many benchmarks do GPT-5 Nano and Qwen-14B share?
11 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Qwen-14B has 18.