Skip to main content
BenchLM

Claude 4 Sonnet vs Hy3 Preview

Updated September 23, 2026. Rank says Hy3 Preview is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInSocial cardCSVJSON

Decision reading

Hy3 Preview has the higher public score estimate, 45.32 versus 36.06, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo
Claude 4 Sonnet

Anthropic

36.06/100

Estimated · Public rank #132

90% interval 29.8–42.3

Model B
Tencent logo
Hy3 Preview

Tencent

45.32/100

Estimated · Public rank #95

90% interval 33.8–56.8

Shared results
2
Claude 4 Sonnet only
1
Hy3 Preview only
4
Like-for-like categories
0 / 8
Estimated: Claude 4 Sonnet and Hy3 PreviewHow the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Long documents

    Prompts that approach the documented context limit

    Hy3 Preview

    Hy3 Preview has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Claude 4 Sonnet is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Claude 4 Sonnet and Hy3 Preview are not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude 4 Sonnet does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate. Hy3 Preview has no comparable published API token rate.

    Confidence: rate-fallback

  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

—Claude 4 Sonnet33.3Hy3 Preview

Not comparable · BenchAlign v5.6

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.6 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Knowledge

Directional only
Claude 4 Sonnet
36.1
Estimated · #100/160
Hy3 Preview
39.1
Estimated · #93/160
Basis
BenchAlign v5.6 lane · 0 vs 2 public rows
Reading
Directional only

Instruction following

Directional only
Claude 4 Sonnet
52.0
#78/124
Hy3 Preview
46.9
#86/124
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Directional only

Agentic

Not comparable
Claude 4 Sonnet
Not ranked
Hy3 Preview
Not ranked
Basis
BenchAlign v5.6 lane · 2 vs 2 public rows
Reading
Not comparable

Coding

Not comparable
Claude 4 Sonnet
Not ranked
Hy3 Preview
33.3
Estimated · #85/135
Basis
BenchAlign v5.6 lane · 1 vs 2 public rows
Reading
Not comparable

Reasoning

Not comparable
Claude 4 Sonnet
51.3
Unranked · 2 rankable rows
Hy3 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Claude 4 Sonnet
52.0
Unranked · 1 rankable row
Hy3 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Claude 4 Sonnet
Not ranked
Hy3 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude 4 Sonnet
Not ranked
Hy3 Preview
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.6) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Claude 4 Sonnet
$0.0105
Fits in one request
Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request

Hy3 Preview has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Claude 4 Sonnet
$0.195
Fits in one request
Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request

Hy3 Preview has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude 4 Sonnet
$0.81
Does not fit in one request
Cached input priced at the published list-input rate
Hy3 Preview
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

Claude 4 Sonnet does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate. Hy3 Preview has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Context window

Maximum documented context; output-token limits may be lower.

Claude 4 Sonnet

200K

Hy3 Preview

256K

API model ID

Claude 4 Sonnet

Not sourced

Hy3 Preview

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude 4 Sonnet

Not published

Hy3 Preview

No comparable hosted API rate

Documented inputs

Claude 4 Sonnet

Not sourced

Hy3 Preview

Not sourced

Documented outputs

Claude 4 Sonnet

Not sourced

Hy3 Preview

Not sourced

Provider availability

Claude 4 Sonnet

Not sourced

Hy3 Preview

Not sourced

Reasoning profile

Claude 4 Sonnet

Non-Reasoning

Hy3 Preview

Reasoning

Weight access

Claude 4 Sonnet

Proprietary

Hy3 Preview

Open Weight

License

Claude 4 Sonnet

Proprietary

Hy3 Preview

Open Weight

Release date

Claude 4 Sonnet

2025-05-01

Hy3 Preview

2026-04-23

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Hy3 Preview has the higher public score estimate, 45.32 versus 36.06, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Hy3 Preview has the larger documented window (256K).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude 4 Sonnet or Hy3 Preview?

Hy3 Preview has the higher public score estimate, 45.32 versus 36.06, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Claude 4 Sonnet or Hy3 Preview?

Claude 4 Sonnet is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Claude 4 Sonnet or Hy3 Preview?

Claude 4 Sonnet and Hy3 Preview are not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Claude 4 Sonnet or Hy3 Preview?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Claude 4 Sonnet or Hy3 Preview?

Hy3 Preview has the larger documented context window: 256K, compared with 200K.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence7 rows

Agentic

  • Gert Labs

    Shared source
    Claude 4 Sonnet39.66%
    Hy3 Preview36.91%

    Claude 4 Sonnet leads this result

  • JobBench

    Claude 4 Sonnet18.4%
    Source
    Hy3 Preview—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude 4 Sonnet—
    Hy3 Preview54.4%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude 4 Sonnet72.7%
    Source
    Hy3 Preview74.4%
    Source

    Hy3 Preview leads this result

  • Terminal-Bench 2.0

    Claude 4 Sonnet—
    Hy3 Preview54.4%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Claude 4 Sonnet—
    Hy3 Preview87.2%
    Source

    Not directly comparable

  • GPQA-D

    Claude 4 Sonnet—
    Hy3 Preview87.2%
    Source

    Not directly comparable

7 public results · 2 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Claude 4 Sonnet vs Hy3 Preview

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Last updated September 23, 2026