Model comparison
GPT-4.1 vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 35.9 on the Noometry Index.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. GPT-4.1 scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 Max leads 38.7 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 73.3% for Qwen3 Max.
- Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
Side by side
| GPT-4.1 | Qwen3 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 35.9 | 43.7 |
| Released | 2025-04-14 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 33K | 66K |
| Input $ / M tokens | $2 | $1.20 |
| Output $ / M tokens | $8 | $6 |
| Results tracked | 52 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
GPT-4.1: 34.4 (#238), Qwen3 Max: 43.0 (#93)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1391 | 1456 |
| ALE-Bench | 558.1 | 370.45 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| CadEval | 42% | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Qwen3 Max: —
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
GPT-4.1: 11.7 (#339), Qwen3 Max: 22.6 (#190)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 72.5% |
| Chess Puzzles | 6% | 4% |
| LMArena Hard Prompts | 1384 | 1448 |
| DTBench | 68.3% | 82.1% |
| LMCA | 25.6% | 28.3% |
| Epoch Capabilities Index | 136.78 | 142.38 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| NYT Connections (extended) | — | 30.1% |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | 61.5 | — |
Math Qwen3 Max leads
GPT-4.1: 22.3 (#280), Qwen3 Max: 38.7 (#131)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 18.9% |
| OTIS Mock AIME 2024-2025 | 38.3% | 73.3% |
| LMArena Math | 1370 | 1446 |
| MATH Level 5 | 83% | 97.1% |
| Omni-MATH | 47.1% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3 Max leads
GPT-4.1: 37.1 (#160), Qwen3 Max: 48.1 (#78)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 66.9% | 72.6% |
| SimpleQA Verified | 31.1% | 48.7% |
| LMArena Expert | 1364 | 1455 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Qwen3 Max: —
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual Qwen3 Max leads
GPT-4.1: 49.4 (#133), Qwen3 Max: 53.7 (#62)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1370 | 1429 |
| LMArena Chinese | 1382 | 1478 |
| LMArena French | 1382 | 1449 |
| LMArena German | 1381 | 1463 |
| LMArena Japanese | 1319 | 1397 |
| LMArena Korean | 1339 | 1399 |
| LMArena Russian | 1377 | 1428 |
| LMArena Spanish | 1376 | 1462 |
Instruction Following Qwen3 Max leads
GPT-4.1: 71.3 (#153), Qwen3 Max: 74.8 (#87)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1367 | 1419 |
| IFEval | 83.8% | — |
Long Context Qwen3 Max leads
GPT-4.1: 40.0 (#163), Qwen3 Max: 41.6 (#134)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | 63.9% | 66.7% |
| LMArena Longer Query | 1385 | 1438 |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
GPT-4.1: 57.6 (#125), Qwen3 Max: 62.4 (#76)
| Benchmark | GPT-4.1 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1383 | 1439 |
| LMArena Creative Writing | 1363 | 1402 |
| LMArena Multi-Turn | 1398 | 1446 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Qwen3 Max?
Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 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 Max share?
29 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Qwen3 Max has 33.