Hy3 Preview released
Tencent · Model release
Source confirmed
Data as of September 23, 2026 · How the score is built
Superseded.Tencent has newer models in this line:Hy3
SupersededOpen WeightReasoning
Released Apr 23, 2026256K context
Hy3 Preview
Decision readingHy3 Preview scores 45.3 out of 100 and ranks #95 of 196. This profile shows 6 source-displayable benchmark rows; its strongest eligible category is Coding at #85. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Released Apr 23, 2026 — see all recent releases
Hy3 Preview will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
45.3/100
field median 50.4#95 of 196 ranked models
Public
#95of 196
Verified —
Price
Self-hosted; infrastructure cost varies
input median $0.97No comparable first-party hosted token rate
Speed
Not measured
field median 91 tok/sTime to first token not measured
Context
256Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Coding ranks #85. Particularly well-suited for software development and code generation tasks.
Validate before choosing
6 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 6 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank Not rankedWeight 22%2 benchmarksVerified | 46.1 | 2 benchmarks | Verified | |||
| CodingRank #85 of 135Percentile 37thWeight 20%2 benchmarksVerified | 33.3 | 2 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #93 of 160Percentile 42ndWeight 12%2 benchmarksVerified | 39.1 | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
6 of 482 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic2/2 verified
- Coding2/2 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
Verified sourceProvisionalNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Hy3 Preview category percentile values
- AgenticNot eligible
- Coding37th percentile
- ReasoningNot eligible
- MultimodalNot eligible
- Knowledge42nd percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- AgenticNot ranked
- Coding#85/135
- ReasoningNot ranked
- MultimodalNot ranked
- Knowledge#93/160
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Top decileTop quartileMid-fieldNot eligible
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score54.4% | Versus best verified row Best verified: GPT-5.5 · 82.0% | Gap27.6 behind | WeightScored in Agentic | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score74.4% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap21.6 behind | WeightDisplay only | Provider exact |
Agentic2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score54.4% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap27.6 behind | Weight7% ref. weight | Provider exact |
| Gert LabsGert Labs Composite Game Benchmark | Score36.91% | Versus best verified row Best verified: Claude Opus 4.8 · 72.97% | Gap36.1 behind | WeightDisplay only | Benchmark exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQAGraduate-Level Google-Proof Q&A | Score87.2% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap8.8 behind | Weight3% ref. weight | Provider exact |
| GPQA-DGPQA Diamond | Score87.2% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap8.8 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 6 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Radar
Full release historyHy3 Preview release history
Radar confirmed these at the source. Use Hy3 Preview in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 256K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Superseded
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Hy3 Preview ranks #95 of 196 on the public leaderboard with a score of 45.32/100. It does not yet have enough sourced coverage for a verified position.
Hy3 Preview is a open weight model with a 256K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Hy3 Preview sits in the Hy3 family with Hy3. 6 of 482 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Coding at #85, while its lowest eligible position is Knowledge at #93. particularly well-suited for software development and code generation tasks.
Last updated September 23, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Hy3 Preview perform overall in AI benchmarks?
Hy3 Preview ranks #95 out of 196 models on the public BenchAlign leaderboard, with a score of 45.32/100. Its evidence status is Estimated, and this profile shows 6 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Hy3 Preview good for knowledge and understanding?
Hy3 Preview ranks #93 out of 160 eligible models for knowledge and understanding, with a public category score of 39.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Hy3 Preview good for coding and programming?
Hy3 Preview ranks #85 out of 135 eligible models for coding and programming, with a public category score of 33.3/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Hy3 Preview good for agentic tool use and computer tasks?
Hy3 Preview has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Hy3 Preview open source?
Hy3 Preview is an open-weight model from Tencent. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to Hy3 Preview?
Hy3 Preview belongs to the Hy3 family. Related tracked variants include Hy3. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Hy3 Preview have full benchmark coverage on BenchLM?
No. Hy3 Preview currently has 22 source-displayable rows across 482 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Hy3 Preview?
Hy3 Preview has a reported context window of 256K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.