Hy3

Hy3 is a reasoning model from Tencent. 11 benchmarks count toward its score, in 4 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.57.5 ±7.9
CoverageShare of the index weight with results.70%
SpeedOutput tokens per second.48/s
Input / 1MUS dollars per 1M input tokens.$0.132
Output / 1MUS dollars per 1M output tokens.$0.528
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.1441 (#65)

The index is a score out of 100. The ± range shows how much it can change.

8,047 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
59.2
CodingCode writing and repair.
60.4
ReasoningLogic problems and puzzles.
55.8
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
57.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
N/A

Results

11 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Artificial Analysis GPQA DiamondKnowledge89.7%60.5Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning79.0%62.9Artificial Analysis
Artificial Analysis Coding IndexCoding58.8%60.4Artificial Analysis
Artificial Analysis SciCodeCoding48.6%60.3Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge33.5%60.9Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge32.0%53.5Artificial Analysis
GDPval-AA normalizedAgentic27.3%56.5Artificial Analysis
Artificial Analysis Agentic IndexAgentic25.6%58.1Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge25.3%54.0Artificial Analysis
Critical Physics TasksReasoning4.9%48.7Artificial Analysis
Agent Arena steerabilityAgentic-1.865.415 Sept 2026LMArena
Agent Arena command recoveryAgentic-3.962.915 Sept 2026LMArena
Agent Arena task outcomeAgentic-10.655.415 Sept 2026LMArena

11 benchmarks count, from 13 of 13 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedLMArena, collected directlyCC BY 4.0 (lmarena-ai/leaderboard-dataset on Hugging Face)

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Tencent

Hy4 preview70.2Hy3 Preview55.6AuKUnrankedHunyuan A13B InstructUnrankedHy ASR 3.0 previewUnranked