Model comparison
GPT-5-Codex vs Qwen2.5 32B Instruct
GPT-5-Codex is the stronger model overall, scoring 37.9 to 30.1 on the Noometry Index. Qwen2.5 32B Instruct costs 2.8× less per token, which makes it the better buy when GPT-5-Codex's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 19.2.
- Qwen2.5 32B Instruct 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.
- Qwen2.5 32B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5-Codex | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.9 | 30.1 |
| Released | 2025-09-15 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $1.25 | $0.70 |
| Output $ / M tokens | $10 | $2.80 |
| Results tracked | 3 | 7 |
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), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | GPT-5-Codex | Qwen2.5 32B Instruct |
|---|---|---|
| WeirdML | 54.5% | — |
| BigCodeBench Instruct | — | 45% |
| BigCodeBench Complete | — | 52.3% |
Agentic & Tool Use Not comparable
GPT-5-Codex: 31.0 (#72), Qwen2.5 32B Instruct: —
| Benchmark | GPT-5-Codex | Qwen2.5 32B Instruct |
|---|---|---|
| Terminal-Bench | 44.3% | — |
Reasoning GPT-5-Codex leads
GPT-5-Codex: 30.9 (#83), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | GPT-5-Codex | Qwen2.5 32B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 128.52 |
Math Not comparable
GPT-5-Codex: —, Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | GPT-5-Codex | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| MATH Level 5 | — | 56.1% |
Knowledge Not comparable
GPT-5-Codex: —, Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | GPT-5-Codex | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
Frequently asked questions
Is GPT-5-Codex better than Qwen2.5 32B Instruct?
GPT-5-Codex is the stronger model overall, scoring 37.9 to 30.1 on the Noometry Index. Qwen2.5 32B Instruct costs 2.8× less per token, which makes it the better buy when GPT-5-Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-5-Codex or Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct 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 Qwen2.5 32B Instruct better for coding?
GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 38.7 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 Qwen2.5 32B Instruct share?
0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Qwen2.5 32B Instruct has 7.