Model comparison
GPT-5.4 nano vs Qwen3-Coder 480B-A35B Instruct
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 38.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. GPT-5.4 nano scores higher in 6 categories and Qwen3-Coder 480B-A35B Instruct in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5.4 nano leads 43.6 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 39.7% for GPT-5.4 nano and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- GPT-5.4 nano accepts more context: 400K tokens versus 262K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.9 | 38.1 |
| Released | 2026-03-17 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.20 | $1.50 |
| Output $ / M tokens | $1.25 | $7.50 |
| Results tracked | 40 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GPT-5.4 nano: 43.6 (#84), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 49.2% | 41.2% |
| LMArena Coding | 1405 | 1412 |
| ALE-Bench | 1,005 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| SciCode | 46.9% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
GPT-5.4 nano: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
GPT-5.4 nano: 23.7 (#173), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 39.7% | 49.5% |
| LMArena Hard Prompts | 1381 | 1372 |
| ARC-AGI-2 | 5.7% | — |
| ARC-AGI-1 | 51.5% | — |
| CritPt | 9.3% | — |
| Chess Puzzles | 30% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 145.81 | — |
| ForecastBench | 57.3 | — |
Math GPT-5.4 nano leads
GPT-5.4 nano: 40.9 (#88), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1406 | 1365 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 5% | — |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5.4 nano leads
GPT-5.4 nano: 41.9 (#103), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1396 | 1338 |
| GPQA Diamond | 78.5% | — |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |
Multimodal Not comparable
GPT-5.4 nano: 36.7 (#78), Qwen3-Coder 480B-A35B Instruct: —
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1196 | — |
Multilingual Too close to call
GPT-5.4 nano: 48.6 (#140), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1359 | 1346 |
| LMArena Chinese | 1392 | 1357 |
| LMArena French | 1396 | 1398 |
| LMArena German | 1367 | 1325 |
| LMArena Japanese | 1343 | 1310 |
| LMArena Korean | 1320 | 1305 |
| LMArena Russian | 1363 | 1366 |
| LMArena Spanish | 1371 | 1360 |
Instruction Following Too close to call
GPT-5.4 nano: 71.9 (#144), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1362 | 1355 |
Long Context Too close to call
GPT-5.4 nano: 41.6 (#137), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1366 | 1378 |
Writing & Preference Too close to call
GPT-5.4 nano: 55.7 (#142), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | GPT-5.4 nano | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1372 | 1357 |
| LMArena Creative Writing | 1314 | 1333 |
| LMArena Multi-Turn | 1382 | 1365 |
Frequently asked questions
Is GPT-5.4 nano better than Qwen3-Coder 480B-A35B Instruct?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 38.1 on the Noometry Index.
Which is cheaper, GPT-5.4 nano or Qwen3-Coder 480B-A35B Instruct?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is GPT-5.4 nano or Qwen3-Coder 480B-A35B Instruct better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 262K.
How many benchmarks do GPT-5.4 nano and Qwen3-Coder 480B-A35B Instruct share?
20 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.