GPT-5 vs Qwen3.5-Flash
Updated October 21, 2026. 54 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 for coding: it scores 72.2 on the Vibe Coding Index against 6.2 for Qwen3.5-Flash.
Pick Qwen3.5-Flash when output tokens cost 38.5x less, or when the context window is larger, 1M against 400K tokens.
- Shared results
- 54
- GPT-5 only
- 55
- Qwen3.5-Flash only
- 1
- Like-for-like categories
- 6 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
GPT-5 scores 72.2 against 6.2.
3 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only GPT-5 has a AA Intelligence Index result, 23.0.
Directional only
Reasoning
GPQA Diamond
GPT-5
GPT-5 leads, 85.6% against 82.8%.
Same board, both measured
Math
AIME
GPT-5
GPT-5 leads, 93.4% against 92.5%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5
GPT-5 leads, 86.5% against 84.1%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5 has a Design Arena: websites result, 1185.
Directional only
Long documents
Listed context window
Qwen3.5-Flash
Qwen3.5-Flash takes 1M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5-Flash
GPT-5 $0.0063, Qwen3.5-Flash $0.0002 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5
GPT-5 $0.39, Qwen3.5-Flash $0.40.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5 72.2 from 3 benchmarks, Qwen3.5-Flash 6.2 from 1 benchmark.
- Widest category
- Coding, 11.1 points apart on average over 7 shared benchmarks.
- Widest single gap
- FrontierMath, tiers 1 to 3: GPT-5 55.4% against Qwen3.5-Flash 18.2%, 37.2 points apart on a 0 to 100 scale.
- Output price
- GPT-5 $10.00 against Qwen3.5-Flash $0.26 per million output tokens, 38.5x apart.
- Context window
- GPT-5 takes 400K tokens, Qwen3.5-Flash 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 | Bars | Qwen3.5-Flash | Ties |
|---|---|---|---|---|
| Coding | 7 | 0 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 7 | 1 | ||
| Math | 3 | 2 | ||
| Knowledge | 10 | 2 | ||
| General | 18 | 3 | ||
| All shared boards | 46 | 8 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index70
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Aider polyglot | 88.0% | Not measured | Only GPT-5 measured |
| SWE-bench Verified | 74.4% | Not measured | Only GPT-5 measured |
| LMArena WebDev | 1418 | 1244 | GPT-5 |
| AA Coding Index | 37.8 | Not measured | Only GPT-5 measured |
| LiveCodeBench (Vals AI) | 85.9% | 83.3% | GPT-5 |
| SWE-bench Verified (Vals AI) | 69.0% | 64.4% | GPT-5 |
| Vibe Code Bench (Vals AI) | 20.1% | Not measured | Only GPT-5 measured |
| LiveCodeBench (Artificial Analysis run) | 84.6% | Not measured | Only GPT-5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 37.9% | Not measured | Only GPT-5 measured |
| Terminal-Bench | 49.6% | Not measured | Only GPT-5 measured |
| GSO-Bench | 6.9% | Not measured | Only GPT-5 measured |
| WeirdML | 60.7% | Not measured | Only GPT-5 measured |
| ALE-Bench | 807.6 | 265.9 | GPT-5 |
| LMArena Text: coding | 1436 | 1412 | GPT-5 |
| LMArena Text: software and IT | 1420 | 1416 | GPT-5 |
| LMArena WebDev: React | Not measured | 1229 | Only Qwen3.5-Flash measured |
| LMArena WebDev: HTML | 1427 | 1291 | GPT-5 |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 23.0 | Not measured | Only GPT-5 measured |
| Epoch Capabilities Index | 150.0 | 143.5 | GPT-5 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 86.5% | Not measured | Only GPT-5 measured |
| METR time horizons | 69.6% | Not measured | Only GPT-5 measured |
| Remote Labor Index | 1.7% | Not measured | Only GPT-5 measured |
| GDPval | 34.8% | Not measured | Only GPT-5 measured |
| BALROG | 32.8% | Not measured | Only GPT-5 measured |
| DeepResearch Bench | 49.6% | Not measured | Only GPT-5 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | 82.8% | GPT-5 |
| MMMU Pro (Vals AI) | 81.5% | 81.9% | Qwen3.5-Flash |
| GPQA Diamond (Artificial Analysis run) | 85.4% | Not measured | Only GPT-5 measured |
| Humanity's Last Exam (Artificial Analysis run) | 28.5% | Not measured | Only GPT-5 measured |
| GPQA Diamond (Epoch AI run) | 86.2% | 82.3% | GPT-5 |
| ARC-AGI | 65.7% | Not measured | Only GPT-5 measured |
| ARC-AGI-2 | 9.9% | Not measured | Only GPT-5 measured |
| SimpleBench | 56.7% | Not measured | Only GPT-5 measured |
| Chess puzzles | 36.0% | 14.0% | GPT-5 |
| Mystery game puzzles | 23.0% | 20.0% | GPT-5 |
| EBR-bench | 12.7% | Not measured | Only GPT-5 measured |
| VPCT | 66.0% | Not measured | Only GPT-5 measured |
| LMArena Text: hard prompts | 1415 | 1403 | GPT-5 |
| LMArena Text: expert | 1419 | 1407 | GPT-5 |
| LMArena Text: hard prompts in English | 1419 | 1409 | GPT-5 |
| LMArena Vision: diagrams | 1252 | Not measured | Only GPT-5 measured |
| LMArena Vision: homework | 1278 | Not measured | Only GPT-5 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AIME | 93.4% | 92.5% | GPT-5 |
| MATH 500 (Vals AI) | 96.0% | Not measured | Only GPT-5 measured |
| MGSM (Vals AI) | 92.8% | Not measured | Only GPT-5 measured |
| AA Math Index | 94.3 | Not measured | Only GPT-5 measured |
| AIME 2025 (Artificial Analysis run) | 94.3% | Not measured | Only GPT-5 measured |
| OTIS Mock AIME | 91.4% | 84.4% | GPT-5 |
| FrontierMath, tiers 1 to 3 | 55.4% | 18.2% | GPT-5 |
| FrontierMath, tier 4 | 22.0% | Not measured | Only GPT-5 measured |
| ProofBench | 18.0% | Not measured | Only GPT-5 measured |
| MATH level 5 | 98.1% | Not measured | Only GPT-5 measured |
| LMArena Text: math | 1407 | 1407 | Qwen3.5-Flash |
| LMArena Text: mathematical work | 1405 | 1413 | Qwen3.5-Flash |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index102
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| MMLU Pro | 86.5% | 84.1% | GPT-5 |
| LegalBench (Vals AI) | 86.0% | 84.3% | GPT-5 |
| CaseLaw (Vals AI) | 66.5% | 56.0% | GPT-5 |
| CorpFin (Vals AI) | 61.1% | 63.6% | Qwen3.5-Flash |
| TaxEval (Vals AI) | 73.4% | 72.2% | GPT-5 |
| MortgageTax (Vals AI) | 65.5% | 67.4% | Qwen3.5-Flash |
| MedQA (Vals AI) | 96.3% | Not measured | Only GPT-5 measured |
| MedCode (Vals AI) | 49.6% | 33.0% | GPT-5 |
| MMLU Pro (Artificial Analysis run) | 87.1% | Not measured | Only GPT-5 measured |
| SimpleQA Verified | 50.1% | 20.3% | GPT-5 |
| GeoBench | 81.0% | Not measured | Only GPT-5 measured |
| LMArena Text: science | 1416 | 1415 | GPT-5 |
| LMArena Text: medicine and healthcare | 1413 | 1407 | GPT-5 |
| LMArena Text: legal and government | 1431 | 1398 | GPT-5 |
| LMArena Text: business and finance | 1400 | 1394 | GPT-5 |
| Neither model has a result on the other 2 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1185 | Not measured | Only GPT-5 measured |
| Design Arena: UI components | 1179 | Not measured | Only GPT-5 measured |
| Design Arena: game dev | 1185 | Not measured | Only GPT-5 measured |
| Design Arena: data viz | 1221 | Not measured | Only GPT-5 measured |
| Design Arena: 3D | 1056 | Not measured | Only GPT-5 measured |
| Design Arena: all code categories | 1168 | Not measured | Only GPT-5 measured |
| Design Arena: SVG | 1188 | Not measured | Only GPT-5 measured |
| Design Arena: ASCII art | 1140 | Not measured | Only GPT-5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index183
| Benchmark | GPT-5 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 43.7% | 42.5% | GPT-5 |
| MedScribe (Vals AI) | 83.7% | 70.6% | GPT-5 |
| IFBench | 73.1% | Not measured | Only GPT-5 measured |
| Long context reasoning (AA-LCR) | 78.2% | Not measured | Only GPT-5 measured |
| DTBench | 90.7% | 82.9% | GPT-5 |
| LMCA | 40.0% | 29.1% | GPT-5 |
| Fiction.LiveBench | 97.2% | Not measured | Only GPT-5 measured |
| Creative writing (Lech Mazur) | 86.0% | Not measured | Only GPT-5 measured |
| LMArena Text | 1406 | 1397 | GPT-5 |
| LMArena Text: instruction following | 1388 | 1374 | GPT-5 |
| LMArena Text: creative writing | 1365 | 1343 | GPT-5 |
| LMArena Vision | 1232 | Not measured | Only GPT-5 measured |
| LMArena Text: English | 1409 | 1404 | GPT-5 |
| LMArena Text: non-English | 1397 | 1385 | GPT-5 |
| LMArena Text: Chinese | 1422 | 1445 | Qwen3.5-Flash |
| LMArena Text: German | 1416 | 1390 | GPT-5 |
| LMArena Text: Japanese | 1409 | 1369 | GPT-5 |
| LMArena Text: Korean | 1360 | 1344 | GPT-5 |
| LMArena Text: French | 1409 | 1413 | Qwen3.5-Flash |
| LMArena Text: Spanish | 1399 | 1400 | Qwen3.5-Flash |
| LMArena Text: Russian | 1407 | 1380 | GPT-5 |
| LMArena Text: Polish | 1431 | 1376 | GPT-5 |
| LMArena Text: multi-turn | 1426 | 1393 | GPT-5 |
| LMArena Text: longer queries | 1399 | 1392 | GPT-5 |
| LMArena Text: writing and language | 1384 | 1369 | GPT-5 |
| LMArena Text: entertainment and media | 1379 | 1347 | GPT-5 |
| LMArena Vision: English | 1231 | Not measured | Only GPT-5 measured |
| LMArena Vision: Chinese | 1267 | Not measured | Only GPT-5 measured |
| LMArena Vision: reading text | 1246 | Not measured | Only GPT-5 measured |
| LMArena Vision: humor | 1219 | Not measured | Only GPT-5 measured |
| LMArena Vision: captioning | 1212 | Not measured | Only GPT-5 measured |
| LMArena Vision: recognizing things | 1263 | Not measured | Only GPT-5 measured |
| LMArena Vision: creative writing | 1210 | Not measured | Only GPT-5 measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 | Qwen3.5-Flash | 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
Qwen3.5-Flash costs less
Repository review
50K input + 3K output tokens
Qwen3.5-Flash costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-Flash 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 | Qwen3.5-Flash |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | August 7, 2025 | February 25, 2026 |
| Context window | 400K | 1M |
| Input $/Mtok | $1.25 | $0.065 |
| Output $/Mtok | $10.00 | $0.26 |
| Coding index | 72.2 | 6.2 |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $0.39 | $0.40 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5 better than Qwen3.5-Flash for coding?
Pick GPT-5 for coding: it scores 72.2 on the Vibe Coding Index against 6.2 for Qwen3.5-Flash. Pick Qwen3.5-Flash when output tokens cost 38.5x less, or when the context window is larger, 1M against 400K tokens.
Which is cheaper, GPT-5 or Qwen3.5-Flash?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3.5-Flash costs $0.065 and $0.26. Per solved SWE-bench Verified task, GPT-5 costs $0.39 and Qwen3.5-Flash $0.40.
Which has the bigger context window, GPT-5 or Qwen3.5-Flash?
Qwen3.5-Flash, with 1M tokens against 400K.
How many benchmarks is the GPT-5 vs Qwen3.5-Flash comparison based on?
54 benchmarks have a result for both models as of October 21, 2026. GPT-5's coding index rests on 3 independent benchmarks and Qwen3.5-Flash's on 1. Where only one model has a result, the page says so instead of naming a winner.