GPT-5 Mini vs Qwen3.6 Plus
Updated October 21, 2026. 68 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 37.4 for Qwen3.6 Plus.
Pick Qwen3.6 Plus when output tokens cost 1.0x less, or when the context window is larger, 1M against 400K tokens.
- Shared results
- 68
- GPT-5 Mini only
- 30
- Qwen3.6 Plus only
- 15
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
GPT-5 Mini
GPT-5 Mini scores 59.8 against 37.4.
One benchmark behind each score
Intelligence
AA Intelligence Index
Qwen3.6 Plus
Qwen3.6 Plus leads, 27.0 against 20.6.
Same board, both measured
Reasoning
GPQA Diamond
Qwen3.6 Plus
Qwen3.6 Plus leads, 87.4% against 80.3%.
Same board, both measured
Math
AIME
Qwen3.6 Plus
Qwen3.6 Plus leads, 94.6% against 91.5%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.6 Plus
Qwen3.6 Plus leads, 87.7% against 82.2%.
Same board, both measured
Web design
Design Arena: websites
Qwen3.6 Plus
Qwen3.6 Plus leads, 1243 against 1125.
Same board, both measured
Long documents
Listed context window
Qwen3.6 Plus
Qwen3.6 Plus takes 1M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5 Mini
GPT-5 Mini $0.0013, Qwen3.6 Plus $0.0013 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5 Mini
GPT-5 Mini $0.08, Qwen3.6 Plus $1.19.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5 Mini 59.8 from 1 benchmark, Qwen3.6 Plus 37.4 from 1 benchmark.
- Widest category
- Agentic work, 29.3 points apart on average over 2 shared benchmarks.
- Widest single gap
- Vending-Bench 2: GPT-5 Mini -$31 against Qwen3.6 Plus $5,115, 32.0 points apart on a 0 to 100 scale.
- Output price
- GPT-5 Mini $2.00 against Qwen3.6 Plus $1.95 per million output tokens, 1.0x apart.
- Context window
- GPT-5 Mini takes 400K tokens, Qwen3.6 Plus 1M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5 Mini | Bars | Qwen3.6 Plus | Ties |
|---|---|---|---|---|
| Coding | 1 | 5 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 1 | 9 | ||
| Math | 1 | 4 | ||
| Knowledge | 3 | 9 | ||
| Web design | 1 | 7 | ||
| General | 3 | 20 | ||
| All shared boards | 10 | 58 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index15
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| SWE-bench Verified | 59.8% | Not measured | Only GPT-5 Mini measured |
| SWE-bench Multilingual | 39.7% | Not measured | Only GPT-5 Mini measured |
| LMArena WebDev | Not measured | 1461 | Only Qwen3.6 Plus measured |
| AA Coding Index | Not measured | 54.5 | Only Qwen3.6 Plus measured |
| LiveCodeBench (Vals AI) | 86.6% | 86.0% | GPT-5 Mini |
| SWE-bench Verified (Vals AI) | 60.8% | 73.4% | Qwen3.6 Plus |
| Vibe Code Bench (Vals AI) | 14.2% | 25.6% | Qwen3.6 Plus |
| Code migration (Vals AI) | Not measured | 11.1% | Only Qwen3.6 Plus measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Qwen3.6 Plus measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 53.2% | Only Qwen3.6 Plus measured |
| LiveCodeBench (Artificial Analysis run) | 83.8% | Not measured | Only GPT-5 Mini measured |
| SciCode | 39.0% | Not measured | Only GPT-5 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 33.3% | 43.9% | Qwen3.6 Plus |
| Terminal-Bench | 34.8% | Not measured | Only GPT-5 Mini measured |
| WeirdML | 52.7% | Not measured | Only GPT-5 Mini measured |
| ALE-Bench | Not measured | 670.1 | Only Qwen3.6 Plus measured |
| LMArena Text: coding | 1406 | 1467 | Qwen3.6 Plus |
| LMArena Text: software and IT | 1394 | 1462 | Qwen3.6 Plus |
| LMArena WebDev: React | Not measured | 1454 | Only Qwen3.6 Plus measured |
| LMArena WebDev: HTML | Not measured | 1463 | Only Qwen3.6 Plus measured |
| LMArena WebDev: from an image | Not measured | 1472 | Only Qwen3.6 Plus measured |
| Neither model has a result on the other 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.6 | 27.0 | Qwen3.6 Plus |
| Epoch Capabilities Index | 145.3 | 147.3 | Qwen3.6 Plus |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | Not measured | 40.9% | Only Qwen3.6 Plus measured |
| Tax Agent Bench (Vals AI) | Not measured | 7.7% | Only Qwen3.6 Plus measured |
| Legal Research Bench (Vals AI) | Not measured | 14.9% | Only Qwen3.6 Plus measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 32.9% | Only Qwen3.6 Plus measured |
| τ²-Bench Telecom | 71.1% | 97.7% | Qwen3.6 Plus |
| Vending-Bench 2 | -$31 | $5,115 | Qwen3.6 Plus |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index19
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 87.4% | Qwen3.6 Plus |
| MMMU Pro (Vals AI) | 78.9% | 84.2% | Qwen3.6 Plus |
| GPQA Diamond (Artificial Analysis run) | 82.8% | 88.2% | Qwen3.6 Plus |
| Humanity's Last Exam (Artificial Analysis run) | 21.5% | 27.8% | Qwen3.6 Plus |
| GPQA Diamond (Epoch AI run) | 75.0% | 88.4% | Qwen3.6 Plus |
| ARC-AGI | 54.3% | Not measured | Only GPT-5 Mini measured |
| ARC-AGI-2 | 4.4% | Not measured | Only GPT-5 Mini measured |
| Chess puzzles | 24.0% | 14.0% | GPT-5 Mini |
| Mystery game puzzles | 10.0% | 12.0% | Qwen3.6 Plus |
| VPCT | 40.2% | Not measured | Only GPT-5 Mini measured |
| LMArena Text: hard prompts | 1380 | 1448 | Qwen3.6 Plus |
| LMArena Text: expert | 1379 | 1454 | Qwen3.6 Plus |
| LMArena Text: hard prompts in English | 1383 | 1455 | Qwen3.6 Plus |
| LMArena Vision: diagrams | 1202 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: homework | 1210 | Not measured | Only GPT-5 Mini measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| AIME | 91.5% | 94.6% | Qwen3.6 Plus |
| MATH 500 (Vals AI) | 94.8% | Not measured | Only GPT-5 Mini measured |
| MGSM (Vals AI) | 92.6% | Not measured | Only GPT-5 Mini measured |
| AA Math Index | 90.7 | Not measured | Only GPT-5 Mini measured |
| AIME 2025 (Artificial Analysis run) | 90.7% | Not measured | Only GPT-5 Mini measured |
| OTIS Mock AIME | 86.7% | 93.3% | Qwen3.6 Plus |
| FrontierMath, tiers 1 to 3 | 46.7% | 38.2% | GPT-5 Mini |
| FrontierMath, tier 4 | 12.2% | Not measured | Only GPT-5 Mini measured |
| ProofBench | 9.0% | Not measured | Only GPT-5 Mini measured |
| MATH level 5 | 97.8% | Not measured | Only GPT-5 Mini measured |
| LMArena Text: math | 1378 | 1449 | Qwen3.6 Plus |
| LMArena Text: mathematical work | 1380 | 1448 | Qwen3.6 Plus |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index39
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| MMLU Pro | 82.2% | 87.7% | Qwen3.6 Plus |
| LegalBench (Vals AI) | 81.8% | 84.2% | Qwen3.6 Plus |
| CaseLaw (Vals AI) | 68.5% | 51.5% | GPT-5 Mini |
| CorpFin (Vals AI) | 60.2% | 61.9% | Qwen3.6 Plus |
| TaxEval (Vals AI) | 75.2% | 74.7% | GPT-5 Mini |
| MortgageTax (Vals AI) | 66.9% | 68.0% | Qwen3.6 Plus |
| MedQA (Vals AI) | 96.1% | Not measured | Only GPT-5 Mini measured |
| MedCode (Vals AI) | 43.0% | 36.9% | GPT-5 Mini |
| MMLU Pro (Artificial Analysis run) | 83.7% | Not measured | Only GPT-5 Mini measured |
| SimpleQA Verified | 21.6% | 44.1% | Qwen3.6 Plus |
| LMArena Text: science | 1371 | 1439 | Qwen3.6 Plus |
| LMArena Text: medicine and healthcare | 1380 | 1442 | Qwen3.6 Plus |
| LMArena Text: legal and government | 1375 | 1437 | Qwen3.6 Plus |
| LMArena Text: business and finance | 1358 | 1430 | Qwen3.6 Plus |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| Design Arena: websites | 1125 | 1243 | Qwen3.6 Plus |
| Design Arena: UI components | 1106 | 1233 | Qwen3.6 Plus |
| Design Arena: game dev | 1130 | 1211 | Qwen3.6 Plus |
| Design Arena: data viz | 1131 | 1228 | Qwen3.6 Plus |
| Design Arena: 3D | 1037 | 1202 | Qwen3.6 Plus |
| Design Arena: all code categories | 1115 | 1236 | Qwen3.6 Plus |
| Design Arena: SVG | 1091 | 1160 | Qwen3.6 Plus |
| Design Arena: ASCII art | 1124 | 1115 | GPT-5 Mini |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index320
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 43.0% | 44.9% | Qwen3.6 Plus |
| MedScribe (Vals AI) | 80.6% | 77.0% | GPT-5 Mini |
| Vals Multimodal Index | Not measured | 51.5% | Only Qwen3.6 Plus measured |
| IFBench | 75.4% | 75.2% | GPT-5 Mini |
| Long context reasoning (AA-LCR) | 72.3% | 78.3% | Qwen3.6 Plus |
| DTBench | 80.5% | 81.9% | Qwen3.6 Plus |
| LMCA | 34.2% | 33.1% | GPT-5 Mini |
| Fiction.LiveBench | 69.4% | Not measured | Only GPT-5 Mini measured |
| Creative writing (Lech Mazur) | 83.1% | Not measured | Only GPT-5 Mini measured |
| CL-bench | Not measured | 20.3% | Only Qwen3.6 Plus measured |
| LMArena Text | 1373 | 1436 | Qwen3.6 Plus |
| LMArena Text: instruction following | 1357 | 1424 | Qwen3.6 Plus |
| LMArena Text: creative writing | 1325 | 1404 | Qwen3.6 Plus |
| LMArena Vision | 1202 | Not measured | Only GPT-5 Mini measured |
| LMArena Text: English | 1379 | 1445 | Qwen3.6 Plus |
| LMArena Text: non-English | 1363 | 1424 | Qwen3.6 Plus |
| LMArena Text: Chinese | 1386 | 1477 | Qwen3.6 Plus |
| LMArena Text: German | 1366 | 1451 | Qwen3.6 Plus |
| LMArena Text: Japanese | 1341 | 1390 | Qwen3.6 Plus |
| LMArena Text: Korean | 1308 | 1379 | Qwen3.6 Plus |
| LMArena Text: French | 1386 | 1455 | Qwen3.6 Plus |
| LMArena Text: Spanish | 1354 | 1432 | Qwen3.6 Plus |
| LMArena Text: Russian | 1362 | 1434 | Qwen3.6 Plus |
| LMArena Text: Polish | 1378 | 1433 | Qwen3.6 Plus |
| LMArena Text: multi-turn | 1363 | 1438 | Qwen3.6 Plus |
| LMArena Text: longer queries | 1355 | 1439 | Qwen3.6 Plus |
| LMArena Text: writing and language | 1344 | 1418 | Qwen3.6 Plus |
| LMArena Text: entertainment and media | 1340 | 1402 | Qwen3.6 Plus |
| LMArena Vision: English | 1216 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: Chinese | 1214 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: reading text | 1199 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: humor | 1205 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: captioning | 1217 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: recognizing things | 1226 | Not measured | Only GPT-5 Mini measured |
| LMArena Vision: creative writing | 1181 | Not measured | Only GPT-5 Mini measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Mini | Qwen3.6 Plus | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
GPT-5 Mini costs less
Repository review
50K input + 3K output tokens
GPT-5 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5 Mini costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5 Mini | Qwen3.6 Plus |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | August 7, 2025 | April 2, 2026 |
| Context window | 400K | 1M |
| Input $/Mtok | $0.25 | $0.325 |
| Output $/Mtok | $2.00 | $1.95 |
| Coding index | 59.8 | 37.4 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.08 | $1.19 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5 Mini better than Qwen3.6 Plus for coding?
Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 37.4 for Qwen3.6 Plus. Pick Qwen3.6 Plus when output tokens cost 1.0x less, or when the context window is larger, 1M against 400K tokens.
Which is cheaper, GPT-5 Mini or Qwen3.6 Plus?
GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Qwen3.6 Plus costs $0.325 and $1.95. Per solved SWE-bench Verified task, GPT-5 Mini costs $0.08 and Qwen3.6 Plus $1.19.
Which has the bigger context window, GPT-5 Mini or Qwen3.6 Plus?
Qwen3.6 Plus, with 1M tokens against 400K.
How many benchmarks is the GPT-5 Mini vs Qwen3.6 Plus comparison based on?
68 benchmarks have a result for both models as of October 21, 2026. GPT-5 Mini's coding index rests on 1 independent benchmark and Qwen3.6 Plus's on 1. Where only one model has a result, the page says so instead of naming a winner.