Model comparison
GPT-5-Codex vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 37.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. GPT-5-Codex scores higher in 2 categories and Qwen3 32B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 20.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 70.3% for GPT-5-Codex and 54.9% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 131K.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| GPT-5-Codex | Qwen3 32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.9 | 39.2 |
| Released | 2025-09-15 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $1.25 | $0.70 |
| Output $ / M tokens | $10 | $2.80 |
| Results tracked | 3 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
GPT-5-Codex: 42.4 (#103), Qwen3 32B: 37.7 (#190)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1358 |
Agentic & Tool Use Qwen3 32B leads
GPT-5-Codex: 31.0 (#72), Qwen3 32B: 32.6 (#62)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning GPT-5-Codex leads
GPT-5-Codex: 30.9 (#83), Qwen3 32B: 20.2 (#241)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | — | 1334 |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Not comparable
GPT-5-Codex: —, Qwen3 32B: 39.7 (#99)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LMArena Math | — | 1399 |
Knowledge Not comparable
GPT-5-Codex: —, Qwen3 32B: 40.0 (#125)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
Multilingual Not comparable
GPT-5-Codex: —, Qwen3 32B: 45.6 (#167)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Not comparable
GPT-5-Codex: —, Qwen3 32B: 68.9 (#179)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | — | 1305 |
Long Context Not comparable
GPT-5-Codex: —, Qwen3 32B: 43.8 (#87)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |
Writing & Preference Not comparable
GPT-5-Codex: —, Qwen3 32B: 52.9 (#163)
| Benchmark | GPT-5-Codex | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |
Frequently asked questions
Is GPT-5-Codex better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 37.9 on the Noometry Index.
Which is cheaper, GPT-5-Codex or Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is GPT-5-Codex or Qwen3 32B better for coding?
GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 131K.
How many benchmarks do GPT-5-Codex and Qwen3 32B share?
1 benchmark has published results for both models. GPT-5-Codex has 3 scored results on Noometry and Qwen3 32B has 26.