Model comparison
GPT-5.3 Chat vs Qwen1.5-72B
GPT-5.3 Chat is the stronger model overall, scoring 42.1 to 30.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. GPT-5.3 Chat scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.3 Chat leads 38.2 to 11.5.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Chat | Qwen1.5-72B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.1 | 30.3 |
| Released | 2026-03-03 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 18 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Chat leads
GPT-5.3 Chat: 40.8 (#124), Qwen1.5-72B: 31.4 (#272)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1408 | 1166 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning GPT-5.3 Chat leads
GPT-5.3 Chat: 27.3 (#105), Qwen1.5-72B: 21.2 (#201)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1148 |
Math GPT-5.3 Chat leads
GPT-5.3 Chat: 35.4 (#146), Qwen1.5-72B: 30.7 (#205)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1389 | 1164 |
Knowledge GPT-5.3 Chat leads
GPT-5.3 Chat: 38.2 (#137), Qwen1.5-72B: 11.5 (#295)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1397 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual GPT-5.3 Chat leads
GPT-5.3 Chat: 50.5 (#119), Qwen1.5-72B: 33.4 (#248)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1383 | 1135 |
| LMArena Chinese | 1433 | 1186 |
| LMArena French | 1398 | 1158 |
| LMArena German | 1384 | 1084 |
| LMArena Japanese | 1351 | 1061 |
| LMArena Korean | 1347 | 1049 |
| LMArena Russian | 1400 | 1104 |
| LMArena Spanish | 1371 | 1110 |
Instruction Following GPT-5.3 Chat leads
GPT-5.3 Chat: 73.0 (#124), Qwen1.5-72B: 59.6 (#251)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1378 | 1142 |
Long Context GPT-5.3 Chat leads
GPT-5.3 Chat: 42.6 (#115), Qwen1.5-72B: 35.0 (#238)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1396 | 1157 |
Writing & Preference GPT-5.3 Chat leads
GPT-5.3 Chat: 63.3 (#65), Qwen1.5-72B: 37.4 (#253)
| Benchmark | GPT-5.3 Chat | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1389 | 1166 |
| LMArena Creative Writing | 1356 | 1137 |
| LMArena Multi-Turn | 1413 | 1160 |
| EQ-Bench Creative Writing | 1690 | — |
Frequently asked questions
Is GPT-5.3 Chat better than Qwen1.5-72B?
GPT-5.3 Chat is the stronger model overall, scoring 42.1 to 30.3 on the Noometry Index.
Is GPT-5.3 Chat or Qwen1.5-72B better for coding?
GPT-5.3 Chat scores higher on coding benchmarks: 40.8 versus 31.4 in the Noometry coding category.
How many benchmarks do GPT-5.3 Chat and Qwen1.5-72B share?
17 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Qwen1.5-72B has 22.