Skip to main content
ModelScale

Hy3 Preview

Tencent · Open Weight · rank 85 · bench-align-v5

Self-hosted
Compare this model Model a workload
Canonical idhy3-preview
Overall score55.49
Context window256K tokens
Release date2026-04-23
Access typeOpen Weight
Blended $/1M$0.2975% input / 25% output

Capability shape

Seven axes from the ranking source. A missing axis is drawn as a gap.

Capability evidence

Agentic40.2
Coding47.3
Knowledge36.9
ReasoningUnavailable
Multimodal & GroundedUnavailable
Instruction Following54.8
MathUnavailable

Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.

Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.

Evidence key: ObservedUnavailable

Runtime measurements
MeasurementValueObservedLast goodEvidence
Time to first tokenUnavailableUnavailableUnavailable
Throughput63 tok/s2026-09-172026-09-17

Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.

Endpoint and price matrix

Every published price component, including cache reads and writes.

Price components
ComponentUSDEvidence
Input / 1M tokens$0.18
Output / 1M tokens$0.60
Cache read / 1M tokens$0.06
Cache write / 1M tokensUnavailable
Blended / 1M (75% input / 25% output)$0.29
Self-hosted listingOpen-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.The rates above are a hosted price matched from another provider, not a first-party list price.

Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.

Modelled monthly cost$0.80
Modelled tokens2.82M
Open the simulatorChange this workload

Benchmark record

22 matched benchmark rows with their published value, unit, and provenance.

Knowledge

Knowledge benchmarks
BenchmarkValueTasksDifficultyProvenance
GPQA
Graduate-Level Google-Proof Q&A
87.2448 questionsGraduate levelGPQA: A Graduate-Level Google-Proof Q&A Benchmark
GPQA-D
GPQA Diamond
87.2Graduate-level science questionsGraduate levelTrinity-Large-Thinking: Scaling an Open Source Frontier Agent
HLE
Humanity's Last Exam
25.5Expert-level questionsFrontier expert levelHumanity's Last Exam
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index
41.2Cross-benchmark intelligence indexDisplay-only external referenceArtificial Analysis
AA-GPQA Diamond
Artificial Analysis GPQA Diamond
89.7Graduate-level science questionsGraduate-level science reasoningArtificial Analysis GPQA Diamond Benchmark Leaderboard
AA-HLE
Artificial Analysis Humanity's Last Exam
33.5Expert-level questionsFrontier expert reasoningArtificial Analysis Humanity's Last Exam Benchmark Leaderboard
AA-Omniscience Index
Artificial Analysis Omniscience Index
-18.5Knowledge questionsBroad factual knowledgeAA-Omniscience: Knowledge and Hallucination Benchmark
AA-Omniscience Accuracy
Artificial Analysis Omniscience Accuracy
31.5Knowledge questionsBroad knowledgeArtificial Analysis model benchmarks
AA-Omniscience Hallucination Rate
Artificial Analysis Omniscience Hallucination Rate
73.0Knowledge questionsFactualityArtificial Analysis model benchmarks

Coding

Coding benchmarks
BenchmarkValueTasksDifficultyProvenance
Terminal-Bench 2.0
Terminal-Bench 2.0
54.4Terminal-based software tasksProfessional software engineeringTerminal-Bench 2.0
SWE-bench Verified
Software Engineering Benchmark Verified
74.4500 verified issuesProfessional software engineeringSWE-bench: Can Language Models Resolve Real-World GitHub Issues?
SciCode
Scientific Code Benchmark
41.2——BenchLM
AA Coding Index
Artificial Analysis Coding Index
58.8Cross-benchmark coding indexDisplay-only external referenceArtificial Analysis model leaderboards
AA-SciCode
Artificial Analysis SciCode
48.6Scientific coding subproblemsScientific programmingArtificial Analysis SciCode Benchmark Leaderboard

Reasoning

Reasoning benchmarks
BenchmarkValueTasksDifficultyProvenance
AA-LCR
Artificial Analysis Long Context Reasoning
66.7Long-context reasoning tasksLong-context reasoningArtificial Analysis model benchmarks
CritPt
Critical Physics Tasks
4.9Research-level physics questionsResearch-level physics reasoningCritPt Benchmark Leaderboard

Instruction Following

Instruction Following benchmarks
BenchmarkValueTasksDifficultyProvenance
IFBench
Instruction Following Benchmark
63.1——BenchLM

Agentic

Agentic benchmarks
BenchmarkValueTasksDifficultyProvenance
Terminal-Bench 2.0
Terminal-Bench 2.0
54.4Terminal-based software tasksProfessional software engineeringTerminal-Bench 2.0
GDPval-AA
GDPval-AA
1136Agentic real-world work tasksProfessional agentic workflowsDeepSeek-V4 Technical Report
GDPval-AA
GDPval-AA normalized
35.8Economically valuable tasksProfessional agentic workflowsArtificial Analysis model benchmarks
AA Agentic Index
Artificial Analysis Agentic Index
25.6Cross-benchmark agentic indexDisplay-only external referenceArtificial Analysis model leaderboards
Gert Labs
Gert Labs Composite Game Benchmark
36.91Novel game environmentsAgentic coding and decision-makingGert Labs rankings

Lifecycle and limitations log

Lifecycle events the source associates with this model, plus what this profile does not claim.

No lifecycle event references this model.

That is not evidence the model has no lifecycle plan — only that this source published none.

What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 17:17 UTC.