Model comparison
GPT-4.1 vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 35.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. GPT-4.1 scores higher in 4 categories and Qwen3-Coder 480B-A35B Instruct in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 37.6 to 22.3.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 39.6% for GPT-4.1 and 55.4% for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct is cheaper at $1.50 / $7.50 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 35.9 | 38.1 |
| Released | 2025-04-14 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $8 | $7.50 |
| Results tracked | 52 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
GPT-4.1: 34.4 (#238), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 39.6% | 55.4% |
| WeirdML | 39% | 41.2% |
| LMArena Coding | 1391 | 1412 |
| ALE-Bench | 558.1 | 461.45 |
| SWE-bench Verified | 48.5% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| CadEval | 42% | — |
| AlgoTune | — | 1.44 |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
GPT-4.1: 11.7 (#339), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 49.5% |
| LMArena Hard Prompts | 1384 | 1372 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Qwen3-Coder 480B-A35B Instruct leads
GPT-4.1: 22.3 (#280), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1370 | 1365 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Too close to call
GPT-4.1: 37.1 (#160), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1364 | 1338 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Qwen3-Coder 480B-A35B Instruct: —
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1370 | 1346 |
| LMArena Chinese | 1382 | 1357 |
| LMArena French | 1382 | 1398 |
| LMArena German | 1381 | 1325 |
| LMArena Japanese | 1319 | 1310 |
| LMArena Korean | 1339 | 1305 |
| LMArena Russian | 1377 | 1366 |
| LMArena Spanish | 1376 | 1360 |
Instruction Following Too close to call
GPT-4.1: 71.3 (#153), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1367 | 1355 |
| IFEval | 83.8% | — |
Long Context Qwen3-Coder 480B-A35B Instruct leads
GPT-4.1: 40.0 (#163), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1385 | 1378 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | GPT-4.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1383 | 1357 |
| LMArena Creative Writing | 1363 | 1333 |
| LMArena Multi-Turn | 1398 | 1365 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 262K.
How many benchmarks do GPT-4.1 and Qwen3-Coder 480B-A35B Instruct share?
21 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.