VerdictPal
Join

Models / Other

Hy3

Other · Released 2026-07-06

Tencent Hunyuan Hy3. AA Intelligence Index 41.2 on the 1 Sep 2026 snapshot. Superseded as the current Hunyuan preview by Hy4 preview (28 Aug 2026, 770B / 49B, $0.834 / $2.501).

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

#50 of 168 on AA Index · current snapshot
42 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite53
Context128K
Input / 1MFree
Output / 1MFree
Knowledge cutoffopen
Output speed98 t/s
TTFT (default API)1.69s
Statussolid

Family profile

Best published score in each covered benchmark family.

69/100 avg
Reasoning
90
Coding
48
Agentic
64
Long context
75

4 tested benchmark families

Benchmark placements

Where Hy3 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
AA time to first tokenPerformance#37/ 186Artificial Analysis2026-09-01
AA output speedPerformance#41/ 187Artificial Analysis2026-09-01
GPQA DiamondReasoning#46/ 18590Artificial Analysis2026-09-01
τ³-Bench BankingAgentic#51/ 10623Artificial Analysis2026-09-01
AA-LCRLong context#52/ 17975Artificial Analysis2026-09-01
SciCodeCoding#58/ 18048Artificial Analysis2026-09-01
Terminal-BenchAgentic#59/ 18464Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#60/ 18742Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#62/ 18034Artificial Analysis2026-09-01
Family context

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

AgenticHy3 · 64
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextHy3 · 75
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for Hy3 in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context74.67%Artificial Analysis5
AA output speedPerformance98 t/sArtificial Analysis5
AA time to first tokenPerformance1.69sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning42.2%Artificial Analysis5
GPQA DiamondReasoning89.7%Artificial Analysis5
Humanity's Last ExamReasoning33.5%Artificial Analysis5
SciCodeCoding47.6%Artificial Analysis5
τ³-Bench BankingAgentic22.89%Artificial Analysis5
Terminal-BenchAgentic64.42%Artificial Analysis5
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.

Reasoning90
Coding48
Agentic64
Long context75
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Hy3. Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for Hy3.

Reasoning

Coding

Agentic

Long context

Performance

Sources