Model comparison
GPT-4.1 vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 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 1 category and Qwen3.5-Flash in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5-Flash leads 33.7 to 11.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-4.1 | Qwen3.5-Flash | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 35.9 | 42.5 |
| Released | 2025-04-14 | 2026-02-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 33K | 66K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $8 | $0.40 |
| Results tracked | 52 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1391 | 1412 |
| ALE-Bench | 558.1 | 221.8 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1244 |
| WeirdML | 39% | — |
| CadEval | 42% | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Qwen3.5-Flash: —
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
GPT-4.1: 11.7 (#339), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 6% | 21% |
| LMArena Hard Prompts | 1384 | 1403 |
| DTBench | 68.3% | 82.9% |
| LMCA | 25.6% | 29.1% |
| Epoch Capabilities Index | 136.78 | 143.98 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| Mystery Game Puzzles | — | 20% |
| ForecastBench | 61.5 | — |
Math Qwen3.5-Flash leads
GPT-4.1: 22.3 (#280), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 18.2% |
| OTIS Mock AIME 2024-2025 | 38.3% | 84.4% |
| LMArena Math | 1370 | 1407 |
| FrontierMath (Feb 2025 set) | 5.5% | 6.2% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
Knowledge Qwen3.5-Flash leads
GPT-4.1: 37.1 (#160), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 66.9% | 82.3% |
| SimpleQA Verified | 31.1% | 20.3% |
| Vectara Hallucination Rate | 5.6% | 10.5% |
| LMArena Expert | 1364 | 1407 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Qwen3.5-Flash: —
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual Qwen3.5-Flash leads
GPT-4.1: 49.4 (#133), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1370 | 1385 |
| LMArena Chinese | 1382 | 1446 |
| LMArena French | 1382 | 1412 |
| LMArena German | 1381 | 1390 |
| LMArena Japanese | 1319 | 1368 |
| LMArena Korean | 1339 | 1344 |
| LMArena Russian | 1377 | 1379 |
| LMArena Spanish | 1376 | 1400 |
Instruction Following Qwen3.5-Flash leads
GPT-4.1: 71.3 (#153), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1367 | 1374 |
| IFEval | 83.8% | — |
Long Context Qwen3.5-Flash leads
GPT-4.1: 40.0 (#163), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1385 | 1392 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Too close to call
GPT-4.1: 57.6 (#125), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | GPT-4.1 | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1383 | 1397 |
| LMArena Creative Writing | 1363 | 1343 |
| LMArena Multi-Turn | 1398 | 1393 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Qwen3.5-Flash better for coding?
They score almost the same on coding (34.4 vs 34.2); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 1M.
How many benchmarks do GPT-4.1 and Qwen3.5-Flash share?
29 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Qwen3.5-Flash has 32.