Model comparison
GPT-5-Codex vs Qwen3-4B
GPT-5-Codex is the stronger model overall, scoring 37.3 to 31.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 18.5.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| GPT-5-Codex | Qwen3-4B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.3 | 31.5 |
| Released | 2025-09-15 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 3 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5-Codex: 41.9 (#100), Qwen3-4B: —
| Benchmark | GPT-5-Codex | Qwen3-4B |
|---|---|---|
| WeirdML | 54.5% | — |
Agentic & Tool Use GPT-5-Codex leads
GPT-5-Codex: 30.8 (#66), Qwen3-4B: 27.3 (#94)
| Benchmark | GPT-5-Codex | Qwen3-4B |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning GPT-5-Codex leads
GPT-5-Codex: 30.0 (#80), Qwen3-4B: 18.5 (#264)
| Benchmark | GPT-5-Codex | Qwen3-4B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| Chess Puzzles | — | 4% |
Math Not comparable
GPT-5-Codex: —, Qwen3-4B: 28.5 (#228)
| Benchmark | GPT-5-Codex | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
Knowledge Not comparable
GPT-5-Codex: —, Qwen3-4B: 33.0 (#198)
| Benchmark | GPT-5-Codex | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
Frequently asked questions
Is GPT-5-Codex better than Qwen3-4B?
GPT-5-Codex is the stronger model overall, scoring 37.3 to 31.5 on the Noometry Index.
How many benchmarks do GPT-5-Codex and Qwen3-4B share?
0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Qwen3-4B has 6.