GPT-5.4 Mini vs Hy3
Updated October 21, 2026. 36 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Hy3 for coding: it scores 43.9 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.
Pick GPT-5.4 Mini when the context window is larger, 400K against 262K tokens, or when what matters is SciCode or ALE-Bench, where it leads.
- Shared results
- 36
- GPT-5.4 Mini only
- 52
- Hy3 only
- 8
- Like-for-like categories
- 5 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
Hy3
Hy3 scores 43.9 against 28.2.
One benchmark behind each score
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
No call
Only GPT-5.4 Mini has a GPQA Diamond result, 83.1%.
Directional only
Math
AIME
No call
Only GPT-5.4 Mini has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.4 Mini has a MMLU Pro result, 84.5%.
Directional only
Web design
Design Arena: websites
No call
Only Hy3 has a Design Arena: websites result, 1230.
Directional only
Long documents
Listed context window
GPT-5.4 Mini
GPT-5.4 Mini takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3
GPT-5.4 Mini $0.0030, Hy3 $0.0004 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 Mini has the number, $0.70.
Directional only
At a glance
- Coding index
- GPT-5.4 Mini 28.2 from 1 benchmark, Hy3 43.9 from 1 benchmark.
- Widest category
- Coding, 10.3 points apart on average over 7 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: GPT-5.4 Mini 1386 against Hy3 1511, 20.7 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 Mini $4.50 against Hy3 $0.528 per million output tokens, 8.5x apart.
- Context window
- GPT-5.4 Mini takes 400K tokens, Hy3 262K.
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 | Hy3 | Ties |
|---|---|---|---|---|
| Coding | 2 | 5 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 18 | ||
| All shared boards | 2 | 34 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index25
| Benchmark | GPT-5.4 Mini | Hy3 | Leader |
|---|---|---|---|
| LMArena WebDev | 1397 | 1507 | Hy3 |
| AA Coding Index | 56.1 | Not measured | Only GPT-5.4 Mini measured |
| LiveCodeBench (Vals AI) | 81.5% | Not measured | Only GPT-5.4 Mini measured |
| SWE-bench Verified (Vals AI) | 73.0% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only GPT-5.4 Mini measured |
| Vibe Code Bench (Vals AI) | 48.0% | Not measured | Only GPT-5.4 Mini measured |
| 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% | 48.6% | GPT-5.4 Mini |
| 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 | 838.6 | GPT-5.4 Mini |
| LMArena Text: coding | 1438 | 1466 | Hy3 |
| LMArena Text: software and IT | 1436 | 1463 | Hy3 |
| LMArena WebDev: React | 1386 | 1511 | Hy3 |
| LMArena WebDev: HTML | 1419 | 1487 | Hy3 |
| Neither model has a result on the other 20 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GPT-5.4 Mini | Hy3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.1 | Not measured | Only GPT-5.4 Mini measured |
| Epoch Capabilities Index | 148.7 | Not measured | Only GPT-5.4 Mini measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GPT-5.4 Mini | Hy3 | 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 |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | GPT-5.4 Mini | Hy3 | Leader |
|---|---|---|---|
| GPQA Diamond | 83.1% | Not measured | Only GPT-5.4 Mini measured |
| MMMU Pro (Vals AI) | 79.3% | Not measured | Only GPT-5.4 Mini measured |
| GPQA Diamond (Artificial Analysis run) | 87.5% | 89.7% | Hy3 |
| Humanity's Last Exam (Artificial Analysis run) | 28.1% | 33.5% | Hy3 |
| GPQA Diamond (Epoch AI run) | 86.9% | Not measured | Only GPT-5.4 Mini measured |
| 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% | Not measured | Only GPT-5.4 Mini measured |
| Mystery game puzzles | 11.0% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts | 1424 | 1447 | Hy3 |
| LMArena Text: expert | 1435 | 1461 | Hy3 |
| LMArena Text: hard prompts in English | 1420 | 1455 | Hy3 |
| LMArena Vision: diagrams | 1266 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: homework | 1285 | 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 index02
| Benchmark | GPT-5.4 Mini | Hy3 | Leader |
|---|---|---|---|
| AIME | 95.6% | Not measured | Only GPT-5.4 Mini measured |
| OTIS Mock AIME | 88.9% | Not measured | Only GPT-5.4 Mini measured |
| 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 | 1473 | Hy3 |
| LMArena Text: mathematical work | 1429 | 1482 | Hy3 |
| 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-5.4 Mini | Hy3 | Leader |
|---|---|---|---|
| MMLU Pro | 84.5% | Not measured | Only GPT-5.4 Mini measured |
| CaseLaw (Vals AI) | 51.7% | Not measured | Only GPT-5.4 Mini measured |
| CorpFin (Vals AI) | 60.9% | Not measured | Only GPT-5.4 Mini measured |
| TaxEval (Vals AI) | 71.2% | Not measured | Only GPT-5.4 Mini measured |
| MortgageTax (Vals AI) | 63.5% | Not measured | Only GPT-5.4 Mini measured |
| SimpleQA Verified | 29.4% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: science | 1417 | 1457 | Hy3 |
| LMArena Text: medicine and healthcare | 1395 | 1452 | Hy3 |
| LMArena Text: legal and government | 1414 | 1422 | Hy3 |
| LMArena Text: business and finance | 1418 | 1424 | Hy3 |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5.4 Mini | Hy3 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1230 | Only Hy3 measured |
| Design Arena: UI components | Not measured | 1205 | Only Hy3 measured |
| Design Arena: game dev | Not measured | 1208 | Only Hy3 measured |
| Design Arena: data viz | Not measured | 1163 | Only Hy3 measured |
| Design Arena: 3D | Not measured | 1233 | Only Hy3 measured |
| Design Arena: all code categories | Not measured | 1227 | Only Hy3 measured |
| Design Arena: SVG | Not measured | 1199 | Only Hy3 measured |
| Design Arena: ASCII art | Not measured | 1157 | Only Hy3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
| Benchmark | GPT-5.4 Mini | Hy3 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 50.8% | Not measured | Only GPT-5.4 Mini measured |
| 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% | 79.0% | Hy3 |
| DTBench | 80.0% | Not measured | Only GPT-5.4 Mini measured |
| LMCA | 40.8% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text | 1412 | 1438 | Hy3 |
| LMArena Text: instruction following | 1405 | 1426 | Hy3 |
| LMArena Text: creative writing | 1370 | 1403 | Hy3 |
| LMArena Vision | 1245 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: English | 1412 | 1448 | Hy3 |
| LMArena Text: non-English | 1405 | 1426 | Hy3 |
| LMArena Text: Chinese | 1446 | 1485 | Hy3 |
| LMArena Text: German | 1408 | 1449 | Hy3 |
| LMArena Text: Japanese | 1375 | 1397 | Hy3 |
| LMArena Text: Korean | 1370 | 1396 | Hy3 |
| LMArena Text: French | 1441 | 1456 | Hy3 |
| LMArena Text: Spanish | 1405 | 1457 | Hy3 |
| LMArena Text: Russian | 1417 | 1432 | Hy3 |
| LMArena Text: Polish | 1415 | 1447 | Hy3 |
| LMArena Text: multi-turn | 1429 | 1436 | Hy3 |
| LMArena Text: longer queries | 1408 | 1442 | Hy3 |
| LMArena Text: writing and language | 1393 | 1414 | Hy3 |
| LMArena Text: entertainment and media | 1373 | 1400 | Hy3 |
| 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 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 Mini | Hy3 | 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
Hy3 costs less
Repository review
50K input + 3K output tokens
Hy3 costs less
Agent loop
200K input + 10K output tokens
Hy3 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 | Tencent Hy3 |
|---|---|---|
| Maker | OpenAI | Tencent |
| Weights | No public weights listed | Open weights |
| Released | March 17, 2026 | July 6, 2026 |
| Context window | 400K | 262K |
| Input $/Mtok | $0.75 | $0.132 |
| Output $/Mtok | $4.50 | $0.528 |
| Coding index | 28.2 | 43.9 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.70 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 Mini better than Hy3 for coding?
Pick Hy3 for coding: it scores 43.9 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when the context window is larger, 400K against 262K tokens, or when what matters is SciCode or ALE-Bench, where it leads.
Which is cheaper, GPT-5.4 Mini or Hy3?
GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Hy3 costs $0.132 and $0.528. Cost per solved task is known for GPT-5.4 Mini only.
Which has the bigger context window, GPT-5.4 Mini or Hy3?
GPT-5.4 Mini, with 400K tokens against 262K.
How many benchmarks is the GPT-5.4 Mini vs Hy3 comparison based on?
36 benchmarks have a result for both models as of October 21, 2026. GPT-5.4 Mini's coding index rests on 1 independent benchmark and Hy3's on 1. Where only one model has a result, the page says so instead of naming a winner.