Model comparison
GPT-5.3 Codex vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 45.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. GPT-5.3 Codex scores higher in 1 category and Qwen3.7 Max in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 47.8 to 21.8.
- Qwen3.7 Max is cheaper at $2.50 / $7.50 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- Qwen3.7 Max accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.3 Codex | Qwen3.7 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.5 | 51.4 |
| Released | 2026-02-05 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $1.75 | $2.50 |
| Output $ / M tokens | $14 | $7.50 |
| Results tracked | 8 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
GPT-5.3 Codex: 48.5 (#51), Qwen3.7 Max: 50.2 (#43)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| SWE-bench Verified | 74.8% | 77.3% |
| LMArena WebDev | 1408 | 1515 |
| ALE-Bench | 1,655 | 1,189 |
| SciCode | — | 48.8% |
| WeirdML | 79.3% | — |
| LMArena Coding | — | 1498 |
Agentic & Tool Use GPT-5.3 Codex leads
GPT-5.3 Codex: 47.8 (#9), Qwen3.7 Max: 21.8 (#129)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| GBAEval | — | 0.4% |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, Qwen3.7 Max: 48.4 (#36)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| Epoch Capabilities Index | 156.84 | 153.74 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| LMArena Hard Prompts | — | 1483 |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
Math Not comparable
GPT-5.3 Codex: —, Qwen3.7 Max: 62.3 (#26)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| LMArena Math | — | 1488 |
Knowledge Not comparable
GPT-5.3 Codex: —, Qwen3.7 Max: 61.7 (#24)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| LMArena Expert | — | 1488 |
Multilingual Not comparable
GPT-5.3 Codex: —, Qwen3.7 Max: 57.1 (#13)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | — | 1475 |
| LMArena Chinese | — | 1533 |
| LMArena Russian | — | 1482 |
Instruction Following Not comparable
GPT-5.3 Codex: —, Qwen3.7 Max: 76.9 (#34)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | — | 1460 |
Long Context Not comparable
GPT-5.3 Codex: —, Qwen3.7 Max: 45.4 (#34)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | — | 1484 |
Writing & Preference Not comparable
GPT-5.3 Codex: —, Qwen3.7 Max: 65.2 (#52)
| Benchmark | GPT-5.3 Codex | Qwen3.7 Max |
|---|---|---|
| LMArena Text | — | 1476 |
| LMArena Creative Writing | — | 1450 |
| EQ-Bench 4 | — | 1110 |
| LMArena Multi-Turn | — | 1482 |
Frequently asked questions
Is GPT-5.3 Codex better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 45.5 on the Noometry Index.
Which is cheaper, GPT-5.3 Codex or Qwen3.7 Max?
Qwen3.7 Max is cheaper. It lists at $2.50 per million input tokens and $7.50 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is GPT-5.3 Codex or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 48.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 400K.
How many benchmarks do GPT-5.3 Codex and Qwen3.7 Max share?
4 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Qwen3.7 Max has 33.