Skip to main content
BenchLM
Data

Celeris-1 vs Claude Sonnet 4.6

Updated October 20, 2026. Rank says Claude Sonnet 4.6 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Claude Sonnet 4.6 has the higher public point estimate, 55.89 versus 28.36. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Celeris logo
Celeris-1

Celeris

28.36/100

Estimated · Public rank #193

Conditional range 14.0–42.7

Model B
Anthropic logo
Claude Sonnet 4.6

Anthropic

55.89/100

Supported · Public rank #65

90% interval 43.6–68.2

Shared results
1
Celeris-1 only
3
Claude Sonnet 4.6 only
27
Like-for-like categories
1 / 8
Estimated: Celeris-1 · Supported: Claude Sonnet 4.6. Conditional ranges do not establish rank confidence.How 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

    Claude Sonnet 4.6

    Claude Sonnet 4.6 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

    Celeris-1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    Celeris-1 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    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.

    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. Claude Sonnet 4.6 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input rate. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input 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.

    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.

10.8Celeris-144.7Claude Sonnet 4.6

Directional only · BenchAlign v5.8

Claude Sonnet 4.6 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

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 v5.8 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

Like-for-like
Celeris-1
28.3
Supported · #163/187
Claude Sonnet 4.6
55.4
Supported · #60/187
Basis
BenchAlign v5.8 lane · 1 vs 6 public rows
Reading
Claude Sonnet 4.6 leads

Agentic

Directional only
Celeris-1
8.0
Estimated · #126/131
Claude Sonnet 4.6
46.3
Supported · #57/131
Basis
BenchAlign v5.8 lane · 0 vs 10 public rows
Reading
Directional only

Coding

Directional only
Celeris-1
10.8
Estimated · #143/152
Claude Sonnet 4.6
44.7
Supported · #55/152
Basis
BenchAlign v5.8 lane · 0 vs 9 public rows
Reading
Directional only

Reasoning

Not comparable
Celeris-1
51.1
Unranked · 3 rankable rows
Claude Sonnet 4.6
62.8
Unranked · 4 rankable rows
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Celeris-1
Not ranked
Claude Sonnet 4.6
58.7
#46/55
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Celeris-1
Not ranked
Claude Sonnet 4.6
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Celeris-1
Not ranked
Claude Sonnet 4.6
48.0
#100/149
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Celeris-1
Not ranked
Claude Sonnet 4.6
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 v5.8) 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.

Supported evidence per lane · 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

Celeris-1
$0.00055
Does not fit in one request
Claude Sonnet 4.6
$0.0105
Fits in one request

Celeris-1 does not fit this workload in one request.

Repository review

50K fresh input + 3K output tokens

Celeris-1
$0.0121
Does not fit in one request
Claude Sonnet 4.6
$0.195
Fits in one request

Celeris-1 does not fit this workload in one request.

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
Claude Sonnet 4.6
$0.81
Does not fit in one request
Cached input priced at the published list-input rate

Celeris-1 does not fit this workload in one request. Claude Sonnet 4.6 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input rate. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input 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.

Celeris-1

131,072 tokens

Celeris-1 model guide

Claude Sonnet 4.6

200K

Cached-input rate

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

Celeris-1

Not published

Celeris API pricing

Claude Sonnet 4.6

Not published

Provider availability

Celeris-1

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

Celeris availability

Claude Sonnet 4.6

Not sourced

Reasoning profile

Celeris-1

Non-Reasoning

Claude Sonnet 4.6

Non-Reasoning

Weight access

Celeris-1

Proprietary

Claude Sonnet 4.6

Proprietary

License

Celeris-1

Proprietary

Claude Sonnet 4.6

Proprietary

Release date

Celeris-1

2026-07-22

Claude Sonnet 4.6

2026-02-01

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
Claude Sonnet 4.6 has the higher public point estimate, 55.89 versus 28.36. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
Workload cost
Repository review: $0.0121 vs $0.195. Cache-heavy agent loop: $0.051 vs $0.81.
Context tradeoff
Claude Sonnet 4.6 has the larger documented window (200K).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Celeris-1 or Claude Sonnet 4.6?

Claude Sonnet 4.6 has the higher public point estimate, 55.89 versus 28.36. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Celeris-1 or Claude Sonnet 4.6?

Claude Sonnet 4.6 scores higher for coding on the public lane, 44.7 to 10.8. Celeris-1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Celeris-1 or Claude Sonnet 4.6?

Claude Sonnet 4.6 scores higher for agentic tasks on the public lane, 46.3 to 8. Celeris-1 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Celeris-1 or Claude Sonnet 4.6?

For the stated presets, chat costs $0.00055 on Celeris-1 and $0.0105 on Claude Sonnet 4.6; repository review costs $0.0121 and $0.195; the cache-heavy agent loop costs $0.051 and $0.81. Celeris-1 does not fit this workload in one request. Claude Sonnet 4.6 does not fit this workload in one request. Celeris-1 has no published cached-input rate, so cached tokens use its listed input rate. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Celeris-1 or Claude Sonnet 4.6?

Claude Sonnet 4.6 has the larger documented context window: 200K, compared with 131,072 tokens.

Benchmark evidence

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

Browse raw public benchmark evidence31 rows

Agentic

  • Terminal-Bench 2.0

    Celeris-1—
    Claude Sonnet 4.659.1%
    Source

    Not directly comparable

  • OSWorld-Verified

    Celeris-1—
    Claude Sonnet 4.672.1%
    Source

    Not directly comparable

  • Claw-Eval

    Celeris-1—
    Claude Sonnet 4.667.8%
    Source

    Not directly comparable

  • CyberGym

    Celeris-1—
    Claude Sonnet 4.665.2%
    Source

    Not directly comparable

  • Gert Labs

    Celeris-1—
    Claude Sonnet 4.662.92%
    Source

    Not directly comparable

  • OSWorld 2.0

    Celeris-1—
    Claude Sonnet 4.68.3%
    Source

    Not directly comparable

  • JobBench

    Celeris-1—
    Claude Sonnet 4.636.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Celeris-1—
    Claude Sonnet 4.657.3%
    Source

    Not directly comparable

  • ApprenticeBench

    Celeris-1—
    Claude Sonnet 4.62%
    Source

    Not directly comparable

  • MazeBench

    Celeris-1—
    Claude Sonnet 4.60%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Celeris-1—
    Claude Sonnet 4.679.6%
    Source

    Not directly comparable

  • SWE-Rebench

    Celeris-1—
    Claude Sonnet 4.660.7%
    Source

    Not directly comparable

  • React Native Evals

    Celeris-1—
    Claude Sonnet 4.680.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Celeris-1—
    Claude Sonnet 4.659.1%
    Source

    Not directly comparable

  • Vibe Code Bench

    Celeris-1—
    Claude Sonnet 4.651.48%
    Source

    Not directly comparable

  • cursorBench31

    Celeris-1—
    Claude Sonnet 4.648.8%
    Source

    Not directly comparable

  • FrontierCode 1.1 Main

    Celeris-1—
    Claude Sonnet 4.624.3%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Celeris-1—
    Claude Sonnet 4.682.1%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Celeris-1—
    Claude Sonnet 4.677.4%
    Source

    Not directly comparable

Reasoning

  • DROP

    Celeris-181.4%
    Source
    Claude Sonnet 4.6—

    Not directly comparable

  • ARC-AGI-2

    Celeris-1—
    Claude Sonnet 4.658.3%
    Source

    Not directly comparable

  • ARC-AGI-1

    Celeris-1—
    Claude Sonnet 4.686.00%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    Celeris-1—
    Claude Sonnet 4.677.4%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    Celeris-175.9%
    Source
    Claude Sonnet 4.679.2%
    Source

    Claude Sonnet 4.6 leads this result

  • GPQA

    Celeris-1—
    Claude Sonnet 4.689.9%
    Source

    Not directly comparable

  • SuperGPQA

    Celeris-1—
    Claude Sonnet 4.695%
    Source

    Not directly comparable

  • HLE

    Celeris-1—
    Claude Sonnet 4.649%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Celeris-1—
    Claude Sonnet 4.685.6%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Celeris-1—
    Claude Sonnet 4.687.3%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Celeris-180.8%
    Source
    Claude Sonnet 4.6—

    Not directly comparable

Math

  • GSM8K

    Celeris-193.7%
    Source
    Claude Sonnet 4.6—

    Not directly comparable

31 public results · 1 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Celeris-1 vs Claude Sonnet 4.6

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

Read a sample issue

Join 5,600+ readers.

Last updated October 20, 2026