Model comparison
GPT-5 Mini vs Qwen3-4B
GPT-5 Mini is the stronger model overall, scoring 41.8 to 31.9 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. GPT-5 Mini scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 29.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.7% for GPT-5 Mini and 52.2% for Qwen3-4B.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Qwen3-4B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.8 | 31.9 |
| Released | 2025-08-07 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 60 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5 Mini: 40.1 (#146), Qwen3-4B: —
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| LMArena Coding | 1406 | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use GPT-5 Mini leads
GPT-5 Mini: 31.1 (#70), Qwen3-4B: 27.6 (#100)
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 55.5% | 35.7% |
| Terminal-Bench | 34.8% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), Qwen3-4B: 19.2 (#268)
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 30% | 4% |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| EnigmaEval | 8.2% | — |
| LMArena Hard Prompts | 1380 | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Qwen3-4B: 29.7 (#240)
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 52.2% |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| MathArena Final-Answer Competitions | — | 38.5% |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| LMArena Math | 1378 | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Qwen3-4B: 33.0 (#208)
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 75% | 52.3% |
| Vectara Hallucination Rate | 12.9% | 5.7% |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| GPQA (HELM) | 75.6% | — |
| LMArena Expert | 1379 | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Qwen3-4B: —
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual Not comparable
GPT-5 Mini: 48.9 (#137), Qwen3-4B: —
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1363 | — |
| LMArena Chinese | 1385 | — |
| LMArena French | 1386 | — |
| LMArena German | 1366 | — |
| LMArena Japanese | 1341 | — |
| LMArena Korean | 1308 | — |
| LMArena Russian | 1362 | — |
| LMArena Spanish | 1355 | — |
Instruction Following Not comparable
GPT-5 Mini: 76.2 (#46), Qwen3-4B: —
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| IFEval | 92.7% | — |
| LMArena Instruction Following | 1357 | — |
Long Context Not comparable
GPT-5 Mini: 41.9 (#132), Qwen3-4B: —
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| Fiction.LiveBench | 69.4% | — |
| LMArena Longer Query | 1355 | — |
Writing & Preference Not comparable
GPT-5 Mini: 55.2 (#148), Qwen3-4B: —
| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| LMArena Text | 1373 | — |
| LMArena Creative Writing | 1325 | — |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
| LMArena Multi-Turn | 1363 | — |
Frequently asked questions
Is GPT-5 Mini better than Qwen3-4B?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 31.9 on the Noometry Index.
How many benchmarks do GPT-5 Mini and Qwen3-4B share?
5 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Qwen3-4B has 6.