Model comparison
GPT-5.4 nano vs Qwen3-4B
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 31.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. GPT-5.4 nano scores higher in 3 categories and Qwen3-4B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 nano leads 40.7 to 28.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for GPT-5.4 nano and 52.2% for Qwen3-4B.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 nano | Qwen3-4B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.9 | 31.5 |
| Released | 2026-03-17 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.25 | — |
| Results tracked | 40 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.4 nano: 43.1 (#82), Qwen3-4B: —
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| SciCode | 46.9% | — |
| WeirdML | 49.2% | — |
| LMArena Coding | 1404 | — |
| ALE-Bench | 1,005 | — |
Agentic & Tool Use Not comparable
GPT-5.4 nano: —, Qwen3-4B: 27.3 (#94)
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning GPT-5.4 nano leads
GPT-5.4 nano: 23.8 (#159), Qwen3-4B: 18.5 (#264)
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 30% | 4% |
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| ARC-AGI-1 | 51.5% | — |
| CritPt | 9.3% | — |
| LMArena Hard Prompts | 1380 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 145.78 | — |
| ForecastBench | 57.3 | — |
Math GPT-5.4 nano leads
GPT-5.4 nano: 40.7 (#76), Qwen3-4B: 28.5 (#228)
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 52.2% |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| MathArena Final-Answer Competitions | — | 38.5% |
| ProofBench | 5% | — |
| LMArena Math | 1406 | — |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5.4 nano leads
GPT-5.4 nano: 41.8 (#94), Qwen3-4B: 33.0 (#198)
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 78.5% | 52.3% |
| Vectara Hallucination Rate | 3.1% | 5.7% |
| SimpleQA Verified | 11.7% | — |
| LMArena Expert | 1397 | — |
Multimodal Not comparable
GPT-5.4 nano: 36.0 (#73), Qwen3-4B: —
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| LMArena Vision | 1196 | — |
Multilingual Not comparable
GPT-5.4 nano: 48.8 (#136), Qwen3-4B: —
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1391 | — |
| LMArena French | 1396 | — |
| LMArena German | 1368 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1321 | — |
| LMArena Russian | 1363 | — |
| LMArena Spanish | 1368 | — |
Instruction Following Not comparable
GPT-5.4 nano: 72.1 (#139), Qwen3-4B: —
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1362 | — |
Long Context Not comparable
GPT-5.4 nano: 41.6 (#131), Qwen3-4B: —
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1365 | — |
Writing & Preference Not comparable
GPT-5.4 nano: 55.9 (#137), Qwen3-4B: —
| Benchmark | GPT-5.4 nano | Qwen3-4B |
|---|---|---|
| LMArena Text | 1372 | — |
| LMArena Creative Writing | 1313 | — |
| LMArena Multi-Turn | 1382 | — |
Frequently asked questions
Is GPT-5.4 nano better than Qwen3-4B?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 31.5 on the Noometry Index.
How many benchmarks do GPT-5.4 nano and Qwen3-4B share?
4 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Qwen3-4B has 6.