Model comparison
GPT-4.1 vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 35.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GPT-4.1 scores higher in 2 categories and QwQ-32B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 38.0 to 22.3.
- The biggest single-benchmark swing is Aider Polyglot: 52.4% for GPT-4.1 and 20.9% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | QwQ-32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 35.9 | 39.8 |
| Released | 2025-04-14 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
GPT-4.1: 34.4 (#238), QwQ-32B: 35.4 (#226)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| Aider Polyglot | 52.4% | 20.9% |
| LMArena Coding | 1391 | 1333 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| WeirdML | 39% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), QwQ-32B: —
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning QwQ-32B leads
GPT-4.1: 11.7 (#339), QwQ-32B: 23.7 (#174)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 6% | 5% |
| LMArena Hard Prompts | 1384 | 1325 |
| Epoch Capabilities Index | 136.78 | 137.6 |
| ForecastBench | 61.5 | 58.3 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 68.3% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 25.6% | — |
| LiveBench | — | 72% |
Math QwQ-32B leads
GPT-4.1: 22.3 (#280), QwQ-32B: 38.0 (#143)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 59.2% |
| LMArena Math | 1370 | 1359 |
| FrontierMath (Tiers 1-3) | 6% | — |
| Omni-MATH | 47.1% | — |
| LiveBench Math | — | 77.8% |
| 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), QwQ-32B: 37.2 (#158)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 66.9% | 65.3% |
| LMArena Expert | 1364 | 1324 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), QwQ-32B: —
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), QwQ-32B: 44.8 (#176)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1370 | 1305 |
| LMArena Chinese | 1382 | 1378 |
| LMArena French | 1382 | 1336 |
| LMArena German | 1381 | 1313 |
| LMArena Japanese | 1319 | 1262 |
| LMArena Korean | 1339 | 1279 |
| LMArena Russian | 1377 | 1297 |
| LMArena Spanish | 1376 | 1354 |
Instruction Following QwQ-32B leads
GPT-4.1: 71.3 (#153), QwQ-32B: 72.6 (#137)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1367 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 83.8% | — |
Long Context QwQ-32B leads
GPT-4.1: 40.0 (#163), QwQ-32B: 49.0 (#11)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | 63.9% | 83.3% |
| LMArena Longer Query | 1385 | 1308 |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), QwQ-32B: 50.6 (#180)
| Benchmark | GPT-4.1 | QwQ-32B |
|---|---|---|
| LMArena Text | 1383 | 1329 |
| LMArena Creative Writing | 1363 | 1288 |
| EQ-Bench Creative Writing | 1420 | 1257 |
| LMArena Multi-Turn | 1398 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| WildBench | 85.4% | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is GPT-4.1 better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 35.9 on the Noometry Index.
Is GPT-4.1 or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 34.4 in the Noometry coding category.
How many benchmarks do GPT-4.1 and QwQ-32B share?
25 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and QwQ-32B has 36.