VerdictPal
Join

Models / Other

Hy3-preview (Non-reasoning)

Hy3-preview (Non-reasoning) · Released 2026-04-23

AA Intelligence Index 26.1. Listed on Artificial Analysis with API pricing $0.065/$0.235 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#148 of 184 on AA Index · current snapshot
17 AA Index · 8 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite36
ContextUnlisted
Input / 1M$0.07
Output / 1M$0.23
Knowledge cutoffunpublished
Statussolid

Family profile

Best published score in each covered benchmark family.

49/100 avg
Reasoning
73
Agentic
32
Long context
42

3 tested benchmark families

Benchmark placements

Where Hy3-preview (Non-reasoning) places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
IFBenchReasoning#101/ 12748Artificial Analysis2026-09-10
AA output speedPerformance#151/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#151/ 190Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#151/ 18817Artificial Analysis2026-09-10
Terminal-BenchAgentic#152/ 18932Artificial Analysis2026-09-10
AA-LCRLong context#161/ 18242Artificial Analysis2026-09-10
GPQA DiamondReasoning#165/ 19073Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#166/ 1857Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where Hy3-preview (Non-reasoning) shows up, it's highlighted.

ReasoningHy3-preview (Non-reasoning) · 73
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
AgenticHy3-preview (Non-reasoning) · 32
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextHy3-preview (Non-reasoning) · 42
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for Hy3-preview (Non-reasoning) in the last 120 days. Older rows live in the full table below.

8 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context42%Artificial Analysis6
AA output speedPerformance0 t/sArtificial Analysis6
AA time to first tokenPerformance0.00sArtificial Analysis6
Artificial Analysis Intelligence IndexReasoning17%Artificial Analysis6
GPQA DiamondReasoning73.2%Artificial Analysis6
Humanity's Last ExamReasoning7%Artificial Analysis6
IFBenchReasoning47.96%Artificial Analysis6
Terminal-BenchAgentic31.82%Artificial Analysis6
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning73
Agentic32
Long context42
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Hy3-preview (Non-reasoning). Scores link to the original source; gaps mean no public row exists yet.

8 sourced rows

8 of 37 catalog benchmarks have a sourced row for Hy3-preview (Non-reasoning).

Reasoning

Agentic

Long context

Performance

Sources

The Pack · Editorial newsletter

New tools in your inbox. Free.

One short email when a tool ships or changes status. No tracking, no third-party analytics. Unsubscribe in one click.