Model comparison
GPT-4.5 vs Qwen1.5-110B
GPT-4.5 is the stronger model overall, scoring 36.9 to 33.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. GPT-4.5 scores higher in 6 categories and Qwen1.5-110B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 57.1 to 38.1.
- Qwen1.5-110B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Qwen1.5-110B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.9 | 33.6 |
| Released | 2025-02-27 | 2024-04-25 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 41.8 (#102), Qwen1.5-110B: 32.4 (#260)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1397 | 1184 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| BigCodeBench Instruct | — | 35% |
| LiveBench Coding | 75.2% | — |
| BigCodeBench Complete | — | 44.4% |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), Qwen1.5-110B: —
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Qwen1.5-110B leads
GPT-4.5: 14.1 (#320), Qwen1.5-110B: 21.7 (#192)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1168 |
| ForecastBench | 61.7 | 57.7 |
| 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% | — |
| Epoch Capabilities Index | 136.74 | — |
| LiveBench | 69% | — |
Math Too close to call
GPT-4.5: 31.0 (#200), Qwen1.5-110B: 31.1 (#199)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1412 | 1185 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge GPT-4.5 leads
GPT-4.5: 32.4 (#205), Qwen1.5-110B: 30.7 (#217)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1394 | 1144 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal Not comparable
GPT-4.5: 37.0 (#68), Qwen1.5-110B: —
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.7 (#78), Qwen1.5-110B: 33.8 (#245)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1413 | 1142 |
| LMArena Chinese | 1421 | 1206 |
| LMArena French | 1417 | 1150 |
| LMArena German | 1457 | 1123 |
| LMArena Japanese | 1416 | 1074 |
| LMArena Korean | 1392 | 1044 |
| LMArena Russian | 1419 | 1118 |
| LMArena Spanish | — | 1141 |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.8 (#129), Qwen1.5-110B: 60.6 (#247)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1158 |
| LiveBench Instruction Following | 72.3% | — |
Long Context GPT-4.5 leads
GPT-4.5: 40.4 (#150), Qwen1.5-110B: 35.0 (#237)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1406 | 1157 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.5 leads
GPT-4.5: 57.1 (#129), Qwen1.5-110B: 38.1 (#250)
| Benchmark | GPT-4.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1417 | 1175 |
| LMArena Creative Writing | 1394 | 1148 |
| LMArena Multi-Turn | 1444 | 1160 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Qwen1.5-110B?
GPT-4.5 is the stronger model overall, scoring 36.9 to 33.6 on the Noometry Index.
Is GPT-4.5 or Qwen1.5-110B better for coding?
GPT-4.5 scores higher on coding benchmarks: 41.8 versus 32.4 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Qwen1.5-110B share?
17 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen1.5-110B has 20.