Model comparison
GPT-5.2 Pro vs Qwen3-4B
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 29.7.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Qwen3-4B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 52.3 | 31.9 |
| Released | 2025-12-11 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $21 | — |
| Output $ / M tokens | $168 | — |
| Results tracked | 8 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Agentic & Tool Use Not comparable
GPT-5.2 Pro: —, Qwen3-4B: 27.6 (#100)
| Benchmark | GPT-5.2 Pro | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Qwen3-4B: 19.2 (#268)
| Benchmark | GPT-5.2 Pro | Qwen3-4B |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| Chess Puzzles | — | 4% |
| Epoch Capabilities Index | 155.4 | — |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Qwen3-4B: 29.7 (#240)
| Benchmark | GPT-5.2 Pro | Qwen3-4B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Qwen3-4B: 33.0 (#208)
| Benchmark | GPT-5.2 Pro | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
Frequently asked questions
Is GPT-5.2 Pro better than Qwen3-4B?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 31.9 on the Noometry Index.
How many benchmarks do GPT-5.2 Pro and Qwen3-4B share?
0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Qwen3-4B has 6.