Enter opens the highlighted result. Esc closes.

GPT-5.4 Mini vs Hy3 preview

Hy3 preview leads GPT-5.4 Mini on the Artificial Analysis Intelligence Index, 25.3 to 24.1, and Hy3 preview costs 7.5x less per output token ($0.60 vs $4.50 per million). Updated October 22, 2026; 36 benchmarks have a result for both.

Replace GPT-5.4 Mini Replace Hy3 preview
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
28
Hy3 previewTencent
Coding
No data
Overall
No data
Output $/M
$0.60
8
vs boards won of 36 shared

GPT-5.4 Mini or Hy3 preview: which to pick

Only GPT-5.4 Mini has a coding score, 35.8 on the Vibe Coding Index; Hy3 preview has none, so the two cannot be ranked on coding.

Pick Hy3 preview for output tokens 7.5x cheaper ($0.60 vs $4.50 per million) and work measured by AA Coding Index or AA Intelligence Index, where it leads.

Model AGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved taskModel BHy3 previewTencentNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
36
GPT-5.4 Mini only
53
Hy3 preview only
0
Like-for-like categories
7 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.

At a glance

Coding index
GPT-5.4 Mini 35.8 from 5 benchmarks, Hy3 preview not benchmarked.
Widest category
Agentic work, 7.8 points apart on average over 2 shared benchmarks.
Widest single gap
Terminal-Bench Hard (Artificial Analysis run): GPT-5.4 Mini 52.3% against Hy3 preview 34.1%, 18.2 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Mini $4.50 against Hy3 preview $0.60 per million output tokens, 7.5x apart.
Context window
GPT-5.4 Mini takes 400K tokens, Hy3 preview 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.

Boards won, where both have a result
CategoryGPT-5.4 MiniBarsHy3 previewTies
Coding61
Intelligence01
Agentic work02
Reasoning50
Math02
Knowledge22
General150
All shared boards288
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
Coding benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
LMArena WebDev13971357GPT-5.4 Mini
AA Coding Index56.158.8Hy3 preview
LiveCodeBench (Vals AI)81.5%Not measuredOnly GPT-5.4 Mini measured
SWE-bench Verified (Vals AI)73.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 4 (Vals AI)2.5%Not measuredOnly GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)48.0%Not measuredOnly GPT-5.4 Mini measured
Code migration (Vals AI)12.9%Not measuredOnly GPT-5.4 Mini measured
ProgramBench (Vals AI)0.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)54.7%Not measuredOnly GPT-5.4 Mini measured
SciCode52.1%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)52.3%34.1%GPT-5.4 Mini
FrontierCode27.0%Not measuredOnly GPT-5.4 Mini measured
WeirdML60.3%Not measuredOnly GPT-5.4 Mini measured
ALE-Bench1188.6Not measuredOnly GPT-5.4 Mini measured
LMArena Text: coding14381421GPT-5.4 Mini
LMArena Text: software and IT14361423GPT-5.4 Mini
LMArena WebDev: React13861349GPT-5.4 Mini
LMArena WebDev: HTML14191356GPT-5.4 Mini
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
AA Intelligence Index24.125.3Hy3 preview
Epoch Capabilities Index148.7Not measuredOnly GPT-5.4 Mini measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
AA Agentic Index17.924.1Hy3 preview
Finance Agent (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
Tax Agent Bench (Vals AI)8.8%Not measuredOnly GPT-5.4 Mini measured
Legal Research Bench (Vals AI)12.5%Not measuredOnly GPT-5.4 Mini measured
Excel Modeling Benchmark (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
τ²-Bench Telecom83.3%92.7%Hy3 preview
DeepResearch Bench36.3%Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
GPQA Diamond83.1%Not measuredOnly GPT-5.4 Mini measured
MMMU Pro (Vals AI)79.3%Not measuredOnly GPT-5.4 Mini measured
GPQA Diamond (Artificial Analysis run)87.5%86.7%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)28.1%27.8%GPT-5.4 Mini
GPQA Diamond (Epoch AI run)86.9%Not measuredOnly GPT-5.4 Mini measured
ARC-AGI63.7%Not measuredOnly GPT-5.4 Mini measured
ARC-AGI-218.9%Not measuredOnly GPT-5.4 Mini measured
Chess puzzles23.0%Not measuredOnly GPT-5.4 Mini measured
Mystery game puzzles11.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: hard prompts14241413GPT-5.4 Mini
LMArena Text: expert14351422GPT-5.4 Mini
LMArena Text: hard prompts in English14201416GPT-5.4 Mini
LMArena Vision: diagrams1266Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: homework1285Not measuredOnly GPT-5.4 Mini measured
Kagi LLM Benchmark37.9%Not measuredOnly 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
Math benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
AIME95.6%Not measuredOnly GPT-5.4 Mini measured
OTIS Mock AIME88.9%Not measuredOnly GPT-5.4 Mini measured
FrontierMath, tiers 1 to 351.2%Not measuredOnly GPT-5.4 Mini measured
FrontierMath, tier 49.8%Not measuredOnly GPT-5.4 Mini measured
ProofBench21.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: math14181424Hy3 preview
LMArena Text: mathematical work14291442Hy3 preview
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
Knowledge benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
MMLU Pro84.5%Not measuredOnly GPT-5.4 Mini measured
CaseLaw (Vals AI)51.7%Not measuredOnly GPT-5.4 Mini measured
CorpFin (Vals AI)60.9%Not measuredOnly GPT-5.4 Mini measured
TaxEval (Vals AI)71.2%Not measuredOnly GPT-5.4 Mini measured
MortgageTax (Vals AI)63.5%Not measuredOnly GPT-5.4 Mini measured
SimpleQA Verified29.4%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: science14171416GPT-5.4 Mini
LMArena Text: medicine and healthcare13951405Hy3 preview
LMArena Text: legal and government14141430Hy3 preview
LMArena Text: business and finance14181397GPT-5.4 Mini
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
Web design benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
General benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
SAGE (Vals AI)50.8%Not measuredOnly GPT-5.4 Mini measured
Vals Multimodal Index54.2%Not measuredOnly GPT-5.4 Mini measured
IFBench73.3%63.1%GPT-5.4 Mini
Long context reasoning (AA-LCR)77.0%64.7%GPT-5.4 Mini
DTBench80.0%Not measuredOnly GPT-5.4 Mini measured
LMCA40.8%Not measuredOnly GPT-5.4 Mini measured
LMArena Text14121401GPT-5.4 Mini
LMArena Text: instruction following14051383GPT-5.4 Mini
LMArena Text: creative writing13701339GPT-5.4 Mini
LMArena Vision1245Not measuredOnly GPT-5.4 Mini measured
LMArena Text: English14121409GPT-5.4 Mini
LMArena Text: non-English14051390GPT-5.4 Mini
LMArena Text: Chinese14461435GPT-5.4 Mini
LMArena Text: German1408Not measuredOnly GPT-5.4 Mini measured
LMArena Text: Japanese1375Not measuredOnly GPT-5.4 Mini measured
LMArena Text: Korean1370Not measuredOnly GPT-5.4 Mini measured
LMArena Text: French14411425GPT-5.4 Mini
LMArena Text: Spanish14051399GPT-5.4 Mini
LMArena Text: Russian14171399GPT-5.4 Mini
LMArena Text: Polish1415Not measuredOnly GPT-5.4 Mini measured
LMArena Text: multi-turn14291411GPT-5.4 Mini
LMArena Text: longer queries14081402GPT-5.4 Mini
LMArena Text: writing and language13931370GPT-5.4 Mini
LMArena Text: entertainment and media13731352GPT-5.4 Mini
LMArena Vision: English1244Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: Chinese1286Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: reading text1253Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: humor1235Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: recognizing things1218Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: creative writing1222Not measuredOnly 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
Image generation benchmarks for GPT-5.4 Mini and Hy3 preview
BenchmarkGPT-5.4 MiniHy3 previewLeader
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-5.4 Mini$0.0030Fits in one request
Hy3 preview$0.0005Fits in one request

Hy3 preview costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Mini$0.051Fits in one request
Hy3 preview$0.011Fits in one request

Hy3 preview costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Mini$0.195Fits in one request
Hy3 preview$0.042Fits in one request

Hy3 preview 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.

Specifications of GPT-5.4 Mini and Hy3 preview
SpecificationOpenAI GPT-5.4 MiniTencent Hy3 preview
MakerOpenAITencent
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026April 22, 2026
Context window400K262K
Input $/Mtok$0.75$0.18
Output $/Mtok$4.50$0.60
Coding index35.8Not benchmarked
Independent measurements behind it51
Cost per solved task$0.70Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Mini better than Hy3 preview for coding?

Only GPT-5.4 Mini has a coding score, 35.8 on the Vibe Coding Index; Hy3 preview has none, so the two cannot be ranked on coding. Pick Hy3 preview for output tokens 7.5x cheaper ($0.60 vs $4.50 per million) and work measured by AA Coding Index or AA Intelligence Index, where it leads.

Which is cheaper, GPT-5.4 Mini or Hy3 preview?

GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for GPT-5.4 Mini only.

Which has the bigger context window, GPT-5.4 Mini or Hy3 preview?

GPT-5.4 Mini, with 400K tokens against 262K.

How many benchmarks is the GPT-5.4 Mini vs Hy3 preview comparison based on?

36 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 Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next