# GPT-5 Mini vs Qwen3-4B

> GPT-5 Mini is the stronger model overall, scoring 41.8 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-mini-vs-qwen3-4b
- Last updated: 2026-10-10
- Shared benchmarks: 5

## 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.

## Snapshot

| | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.8 | 31.9 |
| Rank | 128 | 264 |
| Context | 400K | — |
| Input $/M | $0.25 | — |
| Output $/M | $2 | — |
| Weights | Proprietary | Open |

## Coding

- 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: 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: 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: 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: 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

- GPT-5 Mini: 35.6 (#85)
- Qwen3-4B: —

| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |

## Multilingual

- 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

- GPT-5 Mini: 76.2 (#46)
- Qwen3-4B: —

| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| IFEval | 92.7% | — |
| LMArena Instruction Following | 1357 | — |

## Long Context

- GPT-5 Mini: 41.9 (#132)
- Qwen3-4B: —

| Benchmark | GPT-5 Mini | Qwen3-4B |
|---|---|---|
| Fiction.LiveBench | 69.4% | — |
| LMArena Longer Query | 1355 | — |

## Writing & Preference

- 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 | — |

## FAQ

### 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.