Model comparison
GPT-5.1-Codex vs Qwen3-4B
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in agentic & tool use, where GPT-5.1-Codex leads 38.0 to 27.6.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1-Codex | Qwen3-4B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 38.6 | 31.9 |
| Released | 2025-11-12 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 6 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.1-Codex: 41.9 (#116), Qwen3-4B: —
| Benchmark | GPT-5.1-Codex | Qwen3-4B |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1337 | — |
| ALE-Bench | 1,245 | — |
Agentic & Tool Use GPT-5.1-Codex leads
GPT-5.1-Codex: 38.0 (#33), Qwen3-4B: 27.6 (#100)
| Benchmark | GPT-5.1-Codex | Qwen3-4B |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
| METR Time Horizons | 70.8% | — |
Reasoning Not comparable
GPT-5.1-Codex: —, Qwen3-4B: 19.2 (#268)
| Benchmark | GPT-5.1-Codex | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
Math Too close to call
GPT-5.1-Codex: 30.3 (#235), Qwen3-4B: 29.7 (#240)
| Benchmark | GPT-5.1-Codex | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| ProofBench | 9% | — |
Knowledge Not comparable
GPT-5.1-Codex: —, Qwen3-4B: 33.0 (#208)
| Benchmark | GPT-5.1-Codex | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
Frequently asked questions
Is GPT-5.1-Codex better than Qwen3-4B?
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 31.9 on the Noometry Index.
How many benchmarks do GPT-5.1-Codex and Qwen3-4B share?
0 benchmarks have published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and Qwen3-4B has 6.