Skip to main content
BenchLM
Data

Celeris-1 vs Claude Fable 5.1

Updated October 17, 2026. Rank says Claude Fable 5.1 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

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 resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Celeris logo
Celeris-1

Celeris

28.41/100

Estimated · Public rank #190

Conditional range 14.1–42.8

Model B
Anthropic logo
Claude Fable 5.1

Anthropic

83.18/100

Supported · Public rank #4

90% interval 79.9–86.5

Shared results
0
Celeris-1 only
4
Claude Fable 5.1 only
33
Like-for-like categories
1 / 8
Estimated: Celeris-1 · Supported: Claude Fable 5.1. 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 Fable 5.1

    Claude Fable 5.1 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. Celeris-1 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-176.8Claude Fable 5.1

Directional only · BenchAlign v5.8

Claude Fable 5.1 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.

A shared-evidence shape is not available.

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

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
28.4
Supported · #160/184
Claude Fable 5.1
86.9
Supported · #2/184
Basis
BenchAlign v5.8 lane · 1 vs 4 public rows
Reading
Claude Fable 5.1 leads

Agentic

Directional only
Celeris-1
7.5
Estimated · #123/128
Claude Fable 5.1
80.9
Supported · #2/128
Basis
BenchAlign v5.8 lane · 0 vs 12 public rows
Reading
Directional only

Coding

Directional only
Celeris-1
10.8
Estimated · #141/150
Claude Fable 5.1
76.8
Supported · #3/150
Basis
BenchAlign v5.8 lane · 0 vs 11 public rows
Reading
Directional only

Reasoning

Not comparable
Celeris-1
52.0
Unranked · 3 rankable rows
Claude Fable 5.1
85.2
#4/28
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Celeris-1
Not ranked
Claude Fable 5.1
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Celeris-1
Not ranked
Claude Fable 5.1
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Celeris-1
Not ranked
Claude Fable 5.1
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Celeris-1
Not ranked
Claude Fable 5.1
96.8
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 2 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 Fable 5.1
$0.035
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 Fable 5.1
$0.65
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 Fable 5.1
$0.75
Fits 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.

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.

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 Fable 5.1

$0.25 per 1M cached input tokens

Anthropic Fable 5.1 launch

Reasoning profile

Celeris-1

Non-Reasoning

Claude Fable 5.1

Reasoning

Weight access

Celeris-1

Proprietary

Claude Fable 5.1

Proprietary

License

Celeris-1

Proprietary

Claude Fable 5.1

Proprietary

Release date

Celeris-1

2026-07-22

Claude Fable 5.1

2026-09-01

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
Repository review: $0.0121 vs $0.65. Cache-heavy agent loop: $0.051 vs $0.75.
Context tradeoff
Claude Fable 5.1 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Celeris-1 or Claude Fable 5.1?

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 Claude Fable 5.1?

Claude Fable 5.1 scores higher for coding on the public lane, 76.8 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 Fable 5.1?

Claude Fable 5.1 scores higher for agentic tasks on the public lane, 80.9 to 7.5. 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 Fable 5.1?

For the stated presets, chat costs $0.00055 on Celeris-1 and $0.035 on Claude Fable 5.1; repository review costs $0.0121 and $0.65; the cache-heavy agent loop costs $0.051 and $0.75. 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.

Which has the larger context window, Celeris-1 or Claude Fable 5.1?

Claude Fable 5.1 has the larger documented context window: 1M, 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 evidence37 rows

Agentic

  • Terminal-Bench 4.0

    Celeris-1—
    Claude Fable 5.155.80%
    Source

    Not directly comparable

  • Terminal-Bench-Science 0.1

    Celeris-1—
    Claude Fable 5.152.6%
    Source

    Not directly comparable

  • OSWorld 2.0

    Celeris-1—
    Claude Fable 5.141.7%
    Source

    Not directly comparable

  • AutomationBench

    Celeris-1—
    Claude Fable 5.131.4%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Celeris-1—
    Claude Fable 5.177.8%
    Source

    Not directly comparable

  • Toolathlon Verified Pass@3

    Celeris-1—
    Claude Fable 5.181.5%
    Source

    Not directly comparable

  • Toolathlon Verified Pass³

    Celeris-1—
    Claude Fable 5.173.1%
    Source

    Not directly comparable

  • Toolathlon Verified avg. turns

    Celeris-1—
    Claude Fable 5.123.7 turns
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Celeris-1—
    Claude Fable 5.185.0%
    Source

    Not directly comparable

  • ApprenticeBench

    Celeris-1—
    Claude Fable 5.172%
    Source

    Not directly comparable

  • CWE-bench v1

    Celeris-1—
    Claude Fable 5.158.0%
    Source

    Not directly comparable

  • MazeBench

    Celeris-1—
    Claude Fable 5.110%
    Source

    Not directly comparable

Coding

  • Bug Hunt Bench

    Celeris-1—
    Claude Fable 5.143.0 fixes
    Source

    Not directly comparable

  • SWE-bench Pro

    Celeris-1—
    Claude Fable 5.181.2%
    Source

    Not directly comparable

  • SWE Multilingual

    Celeris-1—
    Claude Fable 5.189.1%
    Source

    Not directly comparable

  • SWE Multimodal

    Celeris-1—
    Claude Fable 5.154.7%
    Source

    Not directly comparable

  • DeepSWE

    Celeris-1—
    Claude Fable 5.167.4%
    Source

    Not directly comparable

  • FrontierSWE v2

    Celeris-1—
    Claude Fable 5.156.3%
    Source

    Not directly comparable

  • ProgramBench

    Celeris-1—
    Claude Fable 5.187.6%
    Source

    Not directly comparable

  • CursorBench 3.2

    Celeris-1—
    Claude Fable 5.173.4%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Celeris-1—
    Claude Fable 5.190.5%
    Source

    Not directly comparable

  • CursorBench 4.0

    Celeris-1—
    Claude Fable 5.151.8%
    Source

    Not directly comparable

  • PostTrainBench v1.1

    Celeris-1—
    Claude Fable 5.140.2%
    Source

    Not directly comparable

Reasoning

  • DROP

    Celeris-181.4%
    Source
    Claude Fable 5.1—

    Not directly comparable

  • ARC-AGI-1

    Celeris-1—
    Claude Fable 5.197.50%
    Source

    Not directly comparable

  • ARC-AGI-2

    Celeris-1—
    Claude Fable 5.190%
    Source

    Not directly comparable

  • GraphWalks BFS 256K–1M

    Celeris-1—
    Claude Fable 5.165.0%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    Celeris-175.9%
    Source
    Claude Fable 5.1—

    Not directly comparable

  • HLE

    Celeris-1—
    Claude Fable 5.165%
    Source

    Not directly comparable

  • HLE w/o tools

    Celeris-1—
    Claude Fable 5.160.9%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Celeris-1—
    Claude Fable 5.193.4%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Celeris-1—
    Claude Fable 5.192.4%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Celeris-180.8%
    Source
    Claude Fable 5.1—

    Not directly comparable

  • Gray Swan IPI (15 attempts)

    Celeris-1—
    Claude Fable 5.11.0%
    Source

    Not directly comparable

Math

  • GSM8K

    Celeris-193.7%
    Source
    Claude Fable 5.1—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Celeris-1—
    Claude Fable 5.190.175%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Celeris-1—
    Claude Fable 5.187.805%
    Source

    Not directly comparable

37 public results · 0 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Celeris-1 vs Claude Fable 5.1

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 17, 2026