Model comparison
GPT-5 Mini vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 41.8 on the Noometry Index. GPT-5 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 . 33 shared benchmarks.
Alibaba (Qwen)Summary
- They share 33 benchmarks with published results for both. GPT-5 Mini scores higher in 1 category and Qwen3.6 Plus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 45.6.
- The biggest single-benchmark swing is SimpleQA Verified: 21.6% for GPT-5 Mini and 44.1% for Qwen3.6 Plus.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5 Mini | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.8 | 47.5 |
| Released | 2025-08-07 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.25 | $0.50 |
| Output $ / M tokens | $2 | $3 |
| Results tracked | 60 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Mini: 40.1 (#146), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 64.7% | 57.9% |
| SciCode | 39.2% | 40.7% |
| LMArena Coding | 1406 | 1467 |
| ALE-Bench | 799.77 | 670.15 |
| SWE-bench Verified (bash only) | 59.8% | — |
| LMArena WebDev | — | 1461 |
| SWE-bench Multilingual | 39.7% | — |
| WeirdML | 52.7% | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), Qwen3.6 Plus: —
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | -31.18 | 5,115 |
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
Reasoning Qwen3.6 Plus leads
GPT-5 Mini: 23.9 (#168), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| CritPt | 0% | 2.9% |
| Chess Puzzles | 30% | 17% |
| LMArena Hard Prompts | 1380 | 1449 |
| Mystery Game Puzzles | 10% | 12% |
| DTBench | 80.5% | 81.9% |
| LMCA | 34.2% | 33.1% |
| Epoch Capabilities Index | 145.52 | 147.65 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 54.3% | — |
| EnigmaEval | 8.2% | — |
| Thematic Generalization | — | 59.5% |
| ForecastBench | 61 | — |
Math Qwen3.6 Plus leads
GPT-5 Mini: 46.7 (#69), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.7% | 38.2% |
| OTIS Mock AIME 2024-2025 | 86.7% | 93.3% |
| LMArena Math | 1378 | 1450 |
| FrontierMath (Feb 2025 set) | 27.2% | 26.2% |
| FrontierMath Tier 4 (v1) | 6.3% | 8.3% |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
Knowledge Qwen3.6 Plus leads
GPT-5 Mini: 45.6 (#86), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 75% | 88.4% |
| SimpleQA Verified | 21.6% | 44.1% |
| LMArena Expert | 1379 | 1454 |
| Humanity's Last Exam | 19.4% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Qwen3.6 Plus: —
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual Qwen3.6 Plus leads
GPT-5 Mini: 48.9 (#137), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1363 | 1424 |
| LMArena Chinese | 1385 | 1477 |
| LMArena French | 1386 | 1455 |
| LMArena German | 1366 | 1452 |
| LMArena Japanese | 1341 | 1389 |
| LMArena Korean | 1308 | 1379 |
| LMArena Russian | 1362 | 1434 |
| LMArena Spanish | 1355 | 1432 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1357 | 1425 |
| IFEval | 92.7% | — |
Long Context Qwen3.6 Plus leads
GPT-5 Mini: 41.9 (#132), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1355 | 1439 |
| Fiction.LiveBench | 69.4% | — |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
GPT-5 Mini: 55.2 (#148), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1373 | 1437 |
| LMArena Creative Writing | 1325 | 1404 |
| LMArena Multi-Turn | 1363 | 1438 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 41.8 on the Noometry Index. GPT-5 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-5 Mini or Qwen3.6 Plus?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is GPT-5 Mini or Qwen3.6 Plus better for coding?
They score almost the same on coding (40.1 vs 40.8); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 400K.
How many benchmarks do GPT-5 Mini and Qwen3.6 Plus share?
33 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Qwen3.6 Plus has 37.