Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start the free Radar Brief
BenchLM
Celeris logo
Model A
Celeris-1

Celeris

—

Evidence status unavailable

90% interval unavailable

Celeris-1 vs Hy4 preview

Updated August 28, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Tencent logo
Model B
Hy4 preview

Tencent

79.16/100

Estimated · Public rank #7

90% interval 69.3–89.0

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.

0 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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

    Hy4 preview

    Hy4 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

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Chat turn cost

    1K fresh input + 500 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. Celeris-1 does not fit this workload in one request. Hy4 preview has no comparable published API token rate.

    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. Celeris-1 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input rate. Hy4 preview has no comparable published API token rate.

    Confidence: rate-fallback

  • Repository review cost

    50K fresh input + 3K 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. Celeris-1 does not fit this workload in one request. Hy4 preview has no comparable published API token rate.

    Confidence: listed-rates

What is actually comparable

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

Shared results
0
Celeris-1 only
4
Hy4 preview only
28
Like-for-like categories
0 / 8

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Agentic

Not comparable
Celeris-1
Not measured
Hy4 preview
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Coding

Not comparable
Celeris-1
Not measured
Hy4 preview
65.7
Weighted basis
0 vs 1 rows
Reading
Not comparable

Reasoning

Not comparable
Celeris-1
Not measured
Hy4 preview
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Celeris-1
75.9
Hy4 preview
60.4
Weighted basis
1 vs 2 rows
Reading
Not comparable

Math

Not comparable
Celeris-1
Not measured
Hy4 preview
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Celeris-1
Not measured
Hy4 preview
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Celeris-1
Not measured
Hy4 preview
66.2
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
Celeris-1
80.8
Hy4 preview
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

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

Celeris-1
$0.00055
Does not fit in one request
Hy4 preview
Self-hosted; infrastructure cost varies
Fits in one request

Celeris-1 does not fit this workload in one request. Hy4 preview has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Celeris-1
$0.0121
Does not fit in one request
Hy4 preview
Self-hosted; infrastructure cost varies
Fits in one request

Celeris-1 does not fit this workload in one request. Hy4 preview has no comparable published API token rate.

Cache-heavy agent loop

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

Celeris-1
$0.051
Does not fit in one request
Cached input priced at the published list-input rate
Hy4 preview
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

Celeris-1 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input rate. Hy4 preview has no comparable published API token rate.

Specification differences

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

Provider availability

Celeris-1

Generally Available · Celeris OpenAI-compatible API (United States)

Celeris availability

Hy4 preview

Not sourced

Reasoning profile

Celeris-1

Non-Reasoning

Hy4 preview

Reasoning

Weight access

Celeris-1

Proprietary

Hy4 preview

Open Weight

License

Celeris-1

Proprietary

Hy4 preview

Open Weight

Release date

Celeris-1

2026-07-22

Hy4 preview

2026-08-28

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Hy4 preview has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

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

Browse raw public benchmark evidence32 rows

Agentic

  • Terminal-Bench 2.1

    Celeris-1—
    Hy4 preview85.4%
    Source

    Not directly comparable

  • CyberGym

    Celeris-1—
    Hy4 preview78.4%
    Source

    Not directly comparable

  • WideResearch

    Celeris-1—
    Hy4 preview83.9%
    Source

    Not directly comparable

  • DRACO

    Celeris-1—
    Hy4 preview77.2%
    Source

    Not directly comparable

  • MCP Atlas

    Celeris-1—
    Hy4 preview83.7%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Celeris-1—
    Hy4 preview74.1%
    Source

    Not directly comparable

  • APEX-Agents

    Celeris-1—
    Hy4 preview37.1%
    Source

    Not directly comparable

  • skillsBench

    Celeris-1—
    Hy4 preview62.9%
    Source

    Not directly comparable

  • JobBench

    Celeris-1—
    Hy4 preview61.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    Celeris-1—
    Hy4 preview22.8%
    Source

    Not directly comparable

  • AutomationBench

    Celeris-1—
    Hy4 preview32.1%
    Source

    Not directly comparable

  • BankerToolBench

    Celeris-1—
    Hy4 preview78.6%
    Source

    Not directly comparable

  • HLE w/ tools

    Celeris-1—
    Hy4 preview55.4%
    Source

    Not directly comparable

Coding

  • Terminal-Bench 2.1

    Celeris-1—
    Hy4 preview85.4%
    Source

    Not directly comparable

  • SWE-bench Pro

    Celeris-1—
    Hy4 preview65.7%
    Source

    Not directly comparable

  • SWE Multilingual

    Celeris-1—
    Hy4 preview82.9%
    Source

    Not directly comparable

  • deepSwe

    Celeris-1—
    Hy4 preview64.3%
    Source

    Not directly comparable

  • NL2Repo

    Celeris-1—
    Hy4 preview58.9%
    Source

    Not directly comparable

  • ProgramBench

    Celeris-1—
    Hy4 preview17.5%
    Source

    Not directly comparable

  • PostTrain Bench

    Celeris-1—
    Hy4 preview35.6%
    Source

    Not directly comparable

  • sweMarathon

    Celeris-1—
    Hy4 preview31.9%
    Source

    Not directly comparable

Reasoning

  • DROP

    Celeris-181.4%
    Source
    Hy4 preview—

    Not directly comparable

  • CritPt

    Celeris-1—
    Hy4 preview16.9%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    Celeris-175.9%
    Source
    Hy4 preview—

    Not directly comparable

  • GPQA

    Celeris-1—
    Hy4 preview92.3%
    Source

    Not directly comparable

  • GPQA-D

    Celeris-1—
    Hy4 preview92.3%
    Source

    Not directly comparable

  • HLE

    Celeris-1—
    Hy4 preview55.4%
    Source

    Not directly comparable

  • HLE w/o tools

    Celeris-1—
    Hy4 preview43.4%
    Source

    Not directly comparable

Math

  • GSM8K

    Celeris-193.7%
    Source
    Hy4 preview—

    Not directly comparable

  • Apex

    Celeris-1—
    Hy4 preview74.2%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    Celeris-1—
    Hy4 preview66.2%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Celeris-180.8%
    Source
    Hy4 preview—

    Not directly comparable

Frequently asked questions

Which is better, Celeris-1 or Hy4 preview?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Celeris-1 or Hy4 preview?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, Celeris-1 or Hy4 preview?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Celeris-1 or Hy4 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, Celeris-1 or Hy4 preview?

Hy4 preview has the larger documented context window: 1M, compared with 131,072 tokens.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 28, 2026

Watch Celeris-1 vs Hy4 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.