Model comparison
GPT-4.1 mini vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 33.6 on the Noometry Index. GPT-4.1 mini costs 1.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 24.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 93.3% for Qwen3.6 Plus.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-4.1 mini | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 33.6 | 47.5 |
| Released | 2025-04-14 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.40 | $0.50 |
| Output $ / M tokens | $1.60 | $3 |
| Results tracked | 47 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
GPT-4.1 mini: 30.6 (#293), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| SciCode | 40.4% | 40.7% |
| LMArena Coding | 1367 | 1467 |
| SWE-bench Verified | — | 57.9% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1461 |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
GPT-4.1 mini: 33.3 (#55), Qwen3.6 Plus: —
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
GPT-4.1 mini: 10.8 (#340), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| CritPt | 0% | 2.9% |
| Chess Puzzles | 7% | 17% |
| LMArena Hard Prompts | 1349 | 1449 |
| Mystery Game Puzzles | 7% | 12% |
| DTBench | 68.8% | 81.9% |
| LMCA | 21.1% | 33.1% |
| Epoch Capabilities Index | 135.01 | 147.65 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 48.6% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 3.5% | — |
| Thematic Generalization | — | 59.5% |
Math Qwen3.6 Plus leads
GPT-4.1 mini: 24.1 (#270), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 38.2% |
| OTIS Mock AIME 2024-2025 | 44.7% | 93.3% |
| LMArena Math | 1343 | 1450 |
| FrontierMath (Feb 2025 set) | 4.5% | 26.2% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
GPT-4.1 mini: 34.7 (#194), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 65.8% | 88.4% |
| SimpleQA Verified | 12.7% | 44.1% |
| LMArena Expert | 1338 | 1454 |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |
Multimodal Not comparable
GPT-4.1 mini: 35.8 (#82), Qwen3.6 Plus: —
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1181 | — |
Multilingual Qwen3.6 Plus leads
GPT-4.1 mini: 45.7 (#166), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1318 | 1424 |
| LMArena Chinese | 1329 | 1477 |
| LMArena French | 1358 | 1455 |
| LMArena German | 1351 | 1452 |
| LMArena Japanese | 1290 | 1389 |
| LMArena Korean | 1298 | 1379 |
| LMArena Russian | 1324 | 1434 |
| LMArena Spanish | 1319 | 1432 |
Instruction Following Qwen3.6 Plus leads
GPT-4.1 mini: 73.7 (#118), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1333 | 1425 |
| IFEval | 90.4% | — |
Long Context Qwen3.6 Plus leads
GPT-4.1 mini: 31.8 (#275), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1344 | 1439 |
| Fiction.LiveBench | 44.4% | — |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
GPT-4.1 mini: 48.6 (#199), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | GPT-4.1 mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1340 | 1437 |
| LMArena Creative Writing | 1300 | 1404 |
| LMArena Multi-Turn | 1354 | 1438 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is GPT-4.1 mini better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 33.6 on the Noometry Index. GPT-4.1 mini costs 1.6× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or Qwen3.6 Plus?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is GPT-4.1 mini or Qwen3.6 Plus better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 1M.
How many benchmarks do GPT-4.1 mini and Qwen3.6 Plus share?
29 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Qwen3.6 Plus has 37.