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.

See the free Radar Brief
BenchLM
Anthropic logo
Model A
Claude Fable 5.1

Anthropic

82.74/100

Estimated · Public rank #1

90% interval 71.2–94.3

Claude Fable 5.1 vs Kimi K2.7 Code

Updated September 1, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Moonshot AI logo
Model B
Kimi K2.7 Code

Moonshot AI

54.01/100

Estimated · Public rank #110

90% interval 43.0–65.0

Decision reading

Claude Fable 5.1 has the higher public score, 82.74 versus 54.01, and the 90% score intervals do not overlap.

2 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

    Claude Fable 5.1

    Claude Fable 5.1 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Kimi K2.7 Code

    Kimi K2.7 Code has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

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

    Kimi K2.7 Code

    Kimi K2.7 Code has the lower estimated token cost for this stated workload. Kimi K2.7 Code has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    Kimi K2.7 Code

    Kimi K2.7 Code has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • 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

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
2
Claude Fable 5.1 only
16
Kimi K2.7 Code only
6
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
Claude Fable 5.1
Not measured
Kimi K2.7 Code
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Coding

Not comparable
Claude Fable 5.1
81.2
Kimi K2.7 Code
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
Claude Fable 5.1
90.0
Kimi K2.7 Code
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Claude Fable 5.1
65.0
Kimi K2.7 Code
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Math

Not comparable
Claude Fable 5.1
Not measured
Kimi K2.7 Code
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Fable 5.1
Not measured
Kimi K2.7 Code
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Claude Fable 5.1
Not measured
Kimi K2.7 Code
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Fable 5.1
Not measured
Kimi K2.7 Code
Not measured
Weighted basis
0 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

Claude Fable 5.1
$0.035
Fits in one request
Kimi K2.7 Code
$0.00295
Fits in one request

Kimi K2.7 Code has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Fable 5.1
$0.65
Fits in one request
Kimi K2.7 Code
$0.0595
Fits in one request

Kimi K2.7 Code has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Claude Fable 5.1
$0.75
Fits in one request
Kimi K2.7 Code
$0.249
Fits in one request
Cached input priced at the published list-input rate

Kimi K2.7 Code has the lower modeled cost

Kimi K2.7 Code has no published cached-input rate, so cached tokens use its listed input rate.

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.

Claude Fable 5.1

$0.25 per 1M cached input tokens

Anthropic Fable 5.1 launch

Kimi K2.7 Code

Not published

Documented inputs

Claude Fable 5.1

Not sourced

Kimi K2.7 Code

Not sourced

Documented outputs

Claude Fable 5.1

Not sourced

Kimi K2.7 Code

Not sourced

Reasoning profile

Claude Fable 5.1

Reasoning

Kimi K2.7 Code

Reasoning

Weight access

Claude Fable 5.1

Proprietary

Kimi K2.7 Code

Open Weight

License

Claude Fable 5.1

Proprietary

Kimi K2.7 Code

Open Weight

Release date

Claude Fable 5.1

2026-09-01

Kimi K2.7 Code

2026-06-12

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 Fable 5.1 has the higher public score, 82.74 versus 54.01, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.65 vs $0.0595. Cache-heavy agent loop: $0.75 vs $0.249.
Context tradeoff
Claude Fable 5.1 has the larger documented window (1M).

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

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Claude Fable 5.1
API / mo$45,000
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.7 Code
API / mo$3,713
Self-host / mo$18,221
Break-even326M/day
Model the full break-even

Benchmark evidence

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

Browse raw public benchmark evidence24 rows

Agentic

  • Terminal-Bench 4.0

    Claude Fable 5.155.80%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Terminal-Bench-Science 0.1

    Claude Fable 5.152.6%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • OSWorld 2.0

    Claude Fable 5.141.7%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • AutomationBench

    Claude Fable 5.131.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Toolathlon-Verified

    Claude Fable 5.177.8%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Toolathlon Verified Pass@3

    Claude Fable 5.181.5%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Toolathlon Verified Pass³

    Claude Fable 5.173.1%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Toolathlon Verified avg. turns

    Claude Fable 5.123.7 turns
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Kimi Claw 24/7

    Claude Fable 5.1—
    Kimi K2.7 Code46.9%
    Source

    Not directly comparable

  • MCP Atlas

    Claude Fable 5.1—
    Kimi K2.7 Code76%
    Source

    Not directly comparable

  • MCP Mark Verified

    Claude Fable 5.1—
    Kimi K2.7 Code81.1%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    Claude Fable 5.181.2%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • SWE Multilingual

    Claude Fable 5.189.1%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • SWE Multimodal

    Claude Fable 5.154.7%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • deepSwe

    Claude Fable 5.167.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • ProgramBench

    Claude Fable 5.187.6%
    Source
    Kimi K2.7 Code53.6%
    Source

    Claude Fable 5.1 leads this result

  • cursorBench32

    Shared source
    Claude Fable 5.173.4%
    Kimi K2.7 Code49.7%

    Claude Fable 5.1 leads this result

  • Kimi Code Bench v2

    Claude Fable 5.1—
    Kimi K2.7 Code62.0%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Claude Fable 5.1—
    Kimi K2.7 Code35.1%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Claude Fable 5.1—
    Kimi K2.7 Code52.1%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Fable 5.197.50%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • ARC-AGI-2

    Claude Fable 5.190%
    Source
    Kimi K2.7 Code—

    Not directly comparable

Knowledge

  • HLE

    Claude Fable 5.165%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • HLE w/o tools

    Claude Fable 5.160.9%
    Source
    Kimi K2.7 Code—

    Not directly comparable

Frequently asked questions

Which is better, Claude Fable 5.1 or Kimi K2.7 Code?

Claude Fable 5.1 has the higher public score, 82.74 versus 54.01, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Claude Fable 5.1 or Kimi K2.7 Code?

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, Claude Fable 5.1 or Kimi K2.7 Code?

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, Claude Fable 5.1 or Kimi K2.7 Code?

For the stated presets, chat costs $0.035 on Claude Fable 5.1 and $0.00295 on Kimi K2.7 Code; repository review costs $0.65 and $0.0595; the cache-heavy agent loop costs $0.75 and $0.249. Kimi K2.7 Code has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Fable 5.1 or Kimi K2.7 Code?

Claude Fable 5.1 has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 1, 2026

Watch Claude Fable 5.1 vs Kimi K2.7 Code

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

Read a sample issue

Join 2,000+ readers.