Model comparison
GPT-5.3 Codex vs Qwen1.5-72B
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 30.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 31.9.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Codex | Qwen1.5-72B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.8 | 30.8 |
| Released | 2026-02-05 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 8 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
GPT-5.3 Codex: 48.6 (#56), Qwen1.5-72B: 31.9 (#277)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1409 | — |
| WeirdML | 79.3% | — |
| BigCodeBench Instruct | — | 33.2% |
| LMArena Coding | — | 1165 |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 1,655 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
GPT-5.3 Codex: 48.0 (#9), Qwen1.5-72B: —
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, Qwen1.5-72B: 22.2 (#203)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | — | 1148 |
| Epoch Capabilities Index | 156.77 | — |
Math Not comparable
GPT-5.3 Codex: —, Qwen1.5-72B: 33.2 (#205)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| LMArena Math | — | 1164 |
Knowledge Not comparable
GPT-5.3 Codex: —, Qwen1.5-72B: 11.5 (#300)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |
Multilingual Not comparable
GPT-5.3 Codex: —, Qwen1.5-72B: 33.2 (#253)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | — | 1135 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |
Instruction Following Not comparable
GPT-5.3 Codex: —, Qwen1.5-72B: 59.3 (#256)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | — | 1141 |
Long Context Not comparable
GPT-5.3 Codex: —, Qwen1.5-72B: 35.1 (#243)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Not comparable
GPT-5.3 Codex: —, Qwen1.5-72B: 37.3 (#258)
| Benchmark | GPT-5.3 Codex | Qwen1.5-72B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1137 |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is GPT-5.3 Codex better than Qwen1.5-72B?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 30.8 on the Noometry Index.
Is GPT-5.3 Codex or Qwen1.5-72B better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 31.9 in the Noometry coding category.
How many benchmarks do GPT-5.3 Codex and Qwen1.5-72B share?
0 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Qwen1.5-72B has 22.