GPT-4o-mini vs Qwen3.5 Plus 2026-04-20
GPT-4o-mini costs 3.0x less per output token than Qwen3.5 Plus 2026-04-20 ($0.60 vs $1.80 per million). Updated October 22, 2026; 11 benchmarks have a result for both.
GPT-4o-mini or Qwen3.5 Plus 2026-04-20: which to pick
Only Qwen3.5 Plus 2026-04-20 has a coding score, 39.5 on the Vibe Coding Index; GPT-4o-mini has none, so the two cannot be ranked on coding.
Pick GPT-4o-mini for output tokens 3.0x cheaper ($0.60 vs $1.80 per million) and work measured by MMMU Pro (Vals AI), where it leads.
- Shared results
- 11
- GPT-4o-mini only
- 18
- Qwen3.5 Plus 2026-04-20 only
- 14
- 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
No call
Only Qwen3.5 Plus 2026-04-20 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only GPT-4o-mini has a AA Intelligence Index result, 6.7.
Directional only
Reasoning
GPQA Diamond
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 leads, 87.4% against 44.2%.
Same board, both measured
Math
AIME
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 leads, 86.0% against 11.5%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 leads, 87.2% against 62.7%.
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 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4o-mini
GPT-4o-mini $0.0004, Qwen3.5 Plus 2026-04-20 $0.0012 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.5 Plus 2026-04-20 has the number, $1.35.
Directional only
At a glance
- Coding index
- GPT-4o-mini not benchmarked, Qwen3.5 Plus 2026-04-20 39.5 from 2 benchmarks.
- Widest category
- Math, 74.6 points apart on average over 1 shared benchmark.
- Widest single gap
- AIME: GPT-4o-mini 11.5% against Qwen3.5 Plus 2026-04-20 86.0%, 74.6 points apart on a 0 to 100 scale.
- Output price
- GPT-4o-mini $0.60 against Qwen3.5 Plus 2026-04-20 $1.80 per million output tokens, 3.0x apart.
- Context window
- GPT-4o-mini takes 128K 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-4o-mini | Bars | Qwen3.5 Plus 2026-04-20 | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 1 | 1 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 2 | ||
| All shared boards | 1 | 10 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | GPT-4o-mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| AA Coding Index | 11.4 | Not measured | Only GPT-4o-mini measured |
| LiveCodeBench (Vals AI) | 26.4% | 85.3% | Qwen3.5 Plus 2026-04-20 |
| SWE-bench Verified (Vals AI) | Not measured | 71.2% | Only Qwen3.5 Plus 2026-04-20 measured |
| Vibe Code Bench (Vals AI) | Not measured | 15.7% | Only Qwen3.5 Plus 2026-04-20 measured |
| LiveCodeBench (Artificial Analysis run) | 23.4% | Not measured | Only GPT-4o-mini measured |
| ALE-Bench | Not measured | 608.9 | Only Qwen3.5 Plus 2026-04-20 measured |
| SciCode | 1.5% | Not measured | Only GPT-4o-mini measured |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4o-mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | Not measured | Only GPT-4o-mini measured |
| Epoch Capabilities Index | 126.5 | 146.2 | Qwen3.5 Plus 2026-04-20 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GPT-4o-mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| Vending-Bench 2 | Not measured | $1 | Only Qwen3.5 Plus 2026-04-20 measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-4o-mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| GPQA Diamond | 44.2% | 87.4% | Qwen3.5 Plus 2026-04-20 |
| MMMU Pro (Vals AI) | 56.6% | 22.8% | GPT-4o-mini |
| GPQA Diamond (Artificial Analysis run) | 42.6% | Not measured | Only GPT-4o-mini measured |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | Not measured | Only GPT-4o-mini measured |
| GPQA Diamond (Epoch AI run) | Not measured | 84.8% | Only Qwen3.5 Plus 2026-04-20 measured |
| ARC-AGI-2 | 0.0% | Not measured | Only GPT-4o-mini measured |
| Chess puzzles | Not measured | 8.0% | Only Qwen3.5 Plus 2026-04-20 measured |
| Mystery game puzzles | Not measured | 17.0% | Only Qwen3.5 Plus 2026-04-20 measured |
| Kagi LLM Benchmark | 28.8% | Not measured | Only GPT-4o-mini measured |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4o-mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| AIME | 11.5% | 86.0% | Qwen3.5 Plus 2026-04-20 |
| MATH 500 (Vals AI) | 72.6% | Not measured | Only GPT-4o-mini measured |
| MGSM (Vals AI) | 86.2% | Not measured | Only GPT-4o-mini measured |
| AA Math Index | 14.7 | Not measured | Only GPT-4o-mini measured |
| AIME 2025 (Artificial Analysis run) | 14.7% | Not measured | Only GPT-4o-mini measured |
| OTIS Mock AIME | Not measured | 86.7% | Only Qwen3.5 Plus 2026-04-20 measured |
| GSM8K | 91.3% | Not measured | Only GPT-4o-mini measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | GPT-4o-mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| MMLU Pro | 62.7% | 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) | Not measured | 59.7% | Only Qwen3.5 Plus 2026-04-20 measured |
| CorpFin (Vals AI) | 45.5% | 65.3% | Qwen3.5 Plus 2026-04-20 |
| TaxEval (Vals AI) | 60.5% | Not measured | Only GPT-4o-mini measured |
| MortgageTax (Vals AI) | 54.5% | 60.8% | Qwen3.5 Plus 2026-04-20 |
| MedQA (Vals AI) | 72.4% | 95.2% | Qwen3.5 Plus 2026-04-20 |
| MMLU Pro (Artificial Analysis run) | 64.8% | Not measured | Only GPT-4o-mini measured |
| SimpleQA Verified | Not measured | 25.4% | Only Qwen3.5 Plus 2026-04-20 measured |
| MMLU | 81.8% | Not measured | Only GPT-4o-mini measured |
| Neither model has a result on the other 8 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4o-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 index02
| Benchmark | GPT-4o-mini | Qwen3.5 Plus 2026-04-20 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 30.4% | Only Qwen3.5 Plus 2026-04-20 measured |
| IFBench | 31.0% | Not measured | Only GPT-4o-mini measured |
| DTBench | 54.4% | 80.5% | Qwen3.5 Plus 2026-04-20 |
| LMCA | 10.4% | 36.4% | Qwen3.5 Plus 2026-04-20 |
| CL-bench | Not measured | 19.8% | Only Qwen3.5 Plus 2026-04-20 measured |
| PIQA | 88.7% | Not measured | Only GPT-4o-mini measured |
| CL-bench Life | Not measured | 12.4% | Only Qwen3.5 Plus 2026-04-20 measured |
| Neither model has a result on the other 39 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4o-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
GPT-4o-mini costs less
Repository review
50K input + 3K output tokens
GPT-4o-mini costs less
Agent loop
200K input + 10K output tokens
GPT-4o-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-4o-mini | Qwen3.5 Plus 2026-04-20 |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | July 18, 2024 | April 27, 2026 |
| Context window | 128K | 1M |
| Input $/Mtok | $0.15 | $0.30 |
| Output $/Mtok | $0.60 | $1.80 |
| Coding index | Not benchmarked | 39.5 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | $1.35 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4o-mini better than Qwen3.5 Plus 2026-04-20 for coding?
Only Qwen3.5 Plus 2026-04-20 has a coding score, 39.5 on the Vibe Coding Index; GPT-4o-mini has none, so the two cannot be ranked on coding. Pick GPT-4o-mini for output tokens 3.0x cheaper ($0.60 vs $1.80 per million) and work measured by MMMU Pro (Vals AI), where it leads.
Which is cheaper, GPT-4o-mini or Qwen3.5 Plus 2026-04-20?
GPT-4o-mini costs $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.5 Plus 2026-04-20 costs $0.30 and $1.80. Cost per solved task is known for Qwen3.5 Plus 2026-04-20 only.
Which has the bigger context window, GPT-4o-mini or Qwen3.5 Plus 2026-04-20?
Qwen3.5 Plus 2026-04-20, with 1M tokens against 128K.
How many benchmarks is the GPT-4o-mini vs Qwen3.5 Plus 2026-04-20 comparison based on?
11 benchmarks have a result for both models as of October 22, 2026. GPT-4o-mini's coding index rests on 0 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.