GPT-5.4 Mini vs Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 leads GPT-5.4 Mini on coding, 39.5 to 35.8 on the Vibe Coding Index, and Qwen3.5 Plus 2026-04-20 costs 2.5x less per output token ($1.80 vs $4.50 per million). Updated October 22, 2026; 20 benchmarks have a result for both.
GPT-5.4 Mini or Qwen3.5 Plus 2026-04-20: which to pick
Pick Qwen3.5 Plus 2026-04-20 for coding: it scores 39.5 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 2 benchmarks against 5.
Pick GPT-5.4 Mini for a lower cost per solved task ($0.70 against $1.35) and work measured by SWE-bench Verified (Vals AI) or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 20
- GPT-5.4 Mini only
- 69
- Qwen3.5 Plus 2026-04-20 only
- 5
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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, six public coding benchmarks
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 scores 39.5 against 35.8.
5 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only GPT-5.4 Mini has a AA Intelligence Index result, 24.1.
Directional only
Agentic work
AA Agentic Index
No call
Only GPT-5.4 Mini has a AA Agentic Index result, 17.9.
Directional only
Reasoning
GPQA Diamond
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 leads, 87.4% against 83.1%.
Same board, both measured
Math
AIME
GPT-5.4 Mini
GPT-5.4 Mini leads, 95.6% against 86.0%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 leads, 87.2% against 84.5%.
Same board, both measured
Long documents
Listed context window
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 takes 1M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5 Plus 2026-04-20
GPT-5.4 Mini $0.0030, Qwen3.5 Plus 2026-04-20 $0.0012 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.4 Mini
GPT-5.4 Mini $0.70, Qwen3.5 Plus 2026-04-20 $1.35.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.4 Mini 35.8 from 5 benchmarks, Qwen3.5 Plus 2026-04-20 39.5 from 2 benchmarks.
- Widest category
- Reasoning, 16.8 points apart on average over 5 shared benchmarks.
- Widest single gap
- MMMU Pro (Vals AI): GPT-5.4 Mini 79.3% against Qwen3.5 Plus 2026-04-20 22.8%, 56.5 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 Mini $4.50 against Qwen3.5 Plus 2026-04-20 $1.80 per million output tokens, 2.5x apart.
- Context window
- GPT-5.4 Mini takes 400K tokens, Qwen3.5 Plus 2026-04-20 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-5.4 Mini | Bars | Qwen3.5 Plus 2026-04-20 | Ties |
|---|---|---|---|---|
| Coding | 3 | 1 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 3 | 2 | ||
| Math | 2 | 0 | ||
| Knowledge | 2 | 3 | ||
| General | 2 | 1 | ||
| All shared boards | 13 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index31
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| LMArena WebDev | 1397 | Not measured | Only GPT-5.4 Mini measured |
| AA Coding Index | 56.1 | Not measured | Only GPT-5.4 Mini measured |
| LiveCodeBench (Vals AI) | 81.5% | 85.3% | Qwen3.5 Plus 2026-04-20 |
| SWE-bench Verified (Vals AI) | 73.0% | 71.2% | GPT-5.4 Mini |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only GPT-5.4 Mini measured |
| Vibe Code Bench (Vals AI) | 48.0% | 15.7% | GPT-5.4 Mini |
| Code migration (Vals AI) | 12.9% | Not measured | Only GPT-5.4 Mini measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | Not measured | Only GPT-5.4 Mini measured |
| SciCode | 52.1% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 52.3% | Not measured | Only GPT-5.4 Mini measured |
| FrontierCode | 27.0% | Not measured | Only GPT-5.4 Mini measured |
| WeirdML | 60.3% | Not measured | Only GPT-5.4 Mini measured |
| ALE-Bench | 1188.6 | 608.9 | GPT-5.4 Mini |
| LMArena Text: coding | 1438 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: software and IT | 1436 | Not measured | Only GPT-5.4 Mini measured |
| LMArena WebDev: React | 1386 | Not measured | Only GPT-5.4 Mini measured |
| LMArena WebDev: HTML | 1419 | Not measured | Only GPT-5.4 Mini measured |
| 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-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.1 | Not measured | Only GPT-5.4 Mini measured |
| Epoch Capabilities Index | 148.7 | 146.2 | GPT-5.4 Mini |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| AA Agentic Index | 17.9 | Not measured | Only GPT-5.4 Mini measured |
| Finance Agent (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| Tax Agent Bench (Vals AI) | 8.8% | Not measured | Only GPT-5.4 Mini measured |
| Legal Research Bench (Vals AI) | 12.5% | Not measured | Only GPT-5.4 Mini measured |
| Excel Modeling Benchmark (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| τ²-Bench Telecom | 83.3% | Not measured | Only GPT-5.4 Mini measured |
| DeepResearch Bench | 36.3% | Not measured | Only GPT-5.4 Mini measured |
| Vending-Bench 2 | Not measured | $1 | Only Qwen3.5 Plus 2026-04-20 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| GPQA Diamond | 83.1% | 87.4% | Qwen3.5 Plus 2026-04-20 |
| MMMU Pro (Vals AI) | 79.3% | 22.8% | GPT-5.4 Mini |
| GPQA Diamond (Artificial Analysis run) | 87.5% | Not measured | Only GPT-5.4 Mini measured |
| Humanity's Last Exam (Artificial Analysis run) | 28.1% | Not measured | Only GPT-5.4 Mini measured |
| GPQA Diamond (Epoch AI run) | 86.9% | 84.8% | GPT-5.4 Mini |
| ARC-AGI | 63.7% | Not measured | Only GPT-5.4 Mini measured |
| ARC-AGI-2 | 18.9% | Not measured | Only GPT-5.4 Mini measured |
| Chess puzzles | 23.0% | 8.0% | GPT-5.4 Mini |
| Mystery game puzzles | 11.0% | 17.0% | Qwen3.5 Plus 2026-04-20 |
| LMArena Text: hard prompts | 1424 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: expert | 1435 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts in English | 1420 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: diagrams | 1266 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: homework | 1285 | Not measured | Only GPT-5.4 Mini measured |
| Kagi LLM Benchmark | 37.9% | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| AIME | 95.6% | 86.0% | GPT-5.4 Mini |
| OTIS Mock AIME | 88.9% | 86.7% | GPT-5.4 Mini |
| FrontierMath, tiers 1 to 3 | 51.2% | Not measured | Only GPT-5.4 Mini measured |
| FrontierMath, tier 4 | 9.8% | Not measured | Only GPT-5.4 Mini measured |
| ProofBench | 21.0% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: math | 1418 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: mathematical work | 1429 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| MMLU Pro | 84.5% | 87.2% | Qwen3.5 Plus 2026-04-20 |
| LegalBench (Vals AI) | Not measured | 85.1% | Only Qwen3.5 Plus 2026-04-20 measured |
| CaseLaw (Vals AI) | 51.7% | 59.7% | Qwen3.5 Plus 2026-04-20 |
| CorpFin (Vals AI) | 60.9% | 65.3% | Qwen3.5 Plus 2026-04-20 |
| TaxEval (Vals AI) | 71.2% | Not measured | Only GPT-5.4 Mini measured |
| MortgageTax (Vals AI) | 63.5% | 60.8% | GPT-5.4 Mini |
| MedQA (Vals AI) | Not measured | 95.2% | Only Qwen3.5 Plus 2026-04-20 measured |
| SimpleQA Verified | 29.4% | 25.4% | GPT-5.4 Mini |
| LMArena Text: science | 1417 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: medicine and healthcare | 1395 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: legal and government | 1414 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: business and finance | 1418 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 6 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 50.8% | 30.4% | GPT-5.4 Mini |
| Vals Multimodal Index | 54.2% | Not measured | Only GPT-5.4 Mini measured |
| IFBench | 73.3% | Not measured | Only GPT-5.4 Mini measured |
| Long context reasoning (AA-LCR) | 77.0% | Not measured | Only GPT-5.4 Mini measured |
| DTBench | 80.0% | 80.5% | Qwen3.5 Plus 2026-04-20 |
| LMCA | 40.8% | 36.4% | GPT-5.4 Mini |
| CL-bench | Not measured | 19.8% | Only Qwen3.5 Plus 2026-04-20 measured |
| CL-bench Life | Not measured | 12.4% | Only Qwen3.5 Plus 2026-04-20 measured |
| LMArena Text | 1412 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: instruction following | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: creative writing | 1370 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision | 1245 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: English | 1412 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: non-English | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Chinese | 1446 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: German | 1408 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Japanese | 1375 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Korean | 1370 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: French | 1441 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Spanish | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Russian | 1417 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Polish | 1415 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: multi-turn | 1429 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: longer queries | 1408 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: writing and language | 1393 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: entertainment and media | 1373 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: English | 1244 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: Chinese | 1286 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: reading text | 1253 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: humor | 1235 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: recognizing things | 1218 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: creative writing | 1222 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 Mini | Qwen3.5 Plus 2026-04-20 | 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 Plus 2026-04-20 costs less
Repository review
50K input + 3K output tokens
Qwen3.5 Plus 2026-04-20 costs less
Agent loop
200K input + 10K output tokens
Qwen3.5 Plus 2026-04-20 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-5.4 Mini | Qwen3.5 Plus 2026-04-20 |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | March 17, 2026 | April 27, 2026 |
| Context window | 400K | 1M |
| Input $/Mtok | $0.75 | $0.30 |
| Output $/Mtok | $4.50 | $1.80 |
| Coding index | 35.8 | 39.5 |
| Independent measurements behind it | 5 | 2 |
| Cost per solved task | $0.70 | $1.35 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 Mini better than Qwen3.5 Plus 2026-04-20 for coding?
Pick Qwen3.5 Plus 2026-04-20 for coding: it scores 39.5 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 2 benchmarks against 5. Pick GPT-5.4 Mini for a lower cost per solved task ($0.70 against $1.35) and work measured by SWE-bench Verified (Vals AI) or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, GPT-5.4 Mini or Qwen3.5 Plus 2026-04-20?
GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Qwen3.5 Plus 2026-04-20 costs $0.30 and $1.80. Per solved SWE-bench Verified task, GPT-5.4 Mini costs $0.70 and Qwen3.5 Plus 2026-04-20 $1.35.
Which has the bigger context window, GPT-5.4 Mini or Qwen3.5 Plus 2026-04-20?
Qwen3.5 Plus 2026-04-20, with 1M tokens against 400K.
How many benchmarks is the GPT-5.4 Mini vs Qwen3.5 Plus 2026-04-20 comparison based on?
20 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Mini's coding index rests on 5 independent benchmarks and Qwen3.5 Plus 2026-04-20's on 2. Where only one model has a result, the page says so instead of naming a winner.