Model comparison
GPT-4.5 vs Qwen-14B
GPT-4.5 is the stronger model overall, scoring 37.2 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-4.5 scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 56.9 to 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Qwen-14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.2 | 31.4 |
| Released | 2025-02-27 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 42.2 (#109), Qwen-14B: 31.2 (#288)
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1396 | 1071 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Qwen-14B: —
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Qwen-14B leads
GPT-4.5: 13.9 (#330), Qwen-14B: 19.6 (#257)
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1027 |
| Epoch Capabilities Index | 136.74 | 113.03 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 61.7 | — |
| LAMBADA | — | 71.1% |
| LiveBench | 69% | — |
| PIQA | — | 79.9% |
Math GPT-4.5 leads
GPT-4.5: 32.6 (#211), Qwen-14B: 31.2 (#227)
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Math | 1412 | 1068 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
GPT-4.5: 32.5 (#211), Qwen-14B: —
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
| LMArena Expert | 1394 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multimodal Not comparable
GPT-4.5: 37.6 (#71), Qwen-14B: —
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.5 (#83), Qwen-14B: 27.5 (#275)
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1413 | 1041 |
| LMArena Chinese | 1421 | 1077 |
| LMArena French | 1418 | — |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |
| LMArena Russian | 1419 | — |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.6 (#134), Qwen-14B: 52.4 (#289)
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1031 |
| LiveBench Instruction Following | 72.3% | — |
Long Context GPT-4.5 leads
GPT-4.5: 40.4 (#155), Qwen-14B: 31.3 (#280)
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1406 | 1028 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.5 leads
GPT-4.5: 56.9 (#134), Qwen-14B: 27.6 (#299)
| Benchmark | GPT-4.5 | Qwen-14B |
|---|---|---|
| LMArena Text | 1417 | 1051 |
| LMArena Creative Writing | 1394 | 1028 |
| LMArena Multi-Turn | 1444 | 1022 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Qwen-14B?
GPT-4.5 is the stronger model overall, scoring 37.2 to 31.4 on the Noometry Index.
Is GPT-4.5 or Qwen-14B better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 31.2 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Qwen-14B share?
11 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen-14B has 18.