Skip to main content
BenchLM
Data

Kimi K2.7 Code vs Sage-A1.5

Updated October 20, 2026. Rank says Sage-A1.5 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
Moonshot AI logo
Kimi K2.7 Code

Moonshot AI

49.26/100

Supported · Public rank #100

90% interval 42.1–56.4

Model B
InternScience logo
Sage-A1.5

InternScience

62.95/100

Estimated · Public rank #44

Conditional range 48.6–77.3

Shared results
0
Kimi K2.7 Code only
13
Sage-A1.5 only
12
Like-for-like categories
0 / 8
Supported: Kimi K2.7 Code · Estimated: Sage-A1.5. 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

    Sage-A1.5

    Sage-A1.5 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

    Sage-A1.5 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

    Sage-A1.5 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

    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

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

    Confidence: listed-rates

  • 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.

41.7Kimi K2.7 Code54.0Sage-A1.5

Directional only · BenchAlign v5.8

Sage-A1.5 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.

3 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.

Agentic

Directional only
Kimi K2.7 Code
38.5
Supported · #73/132
Sage-A1.5
57.7
Estimated · #36/132
Basis
BenchAlign v5.8 lane · 4 vs 6 public rows
Reading
Directional only

Coding

Directional only
Kimi K2.7 Code
41.7
Supported · #64/153
Sage-A1.5
54.0
Estimated · #34/153
Basis
BenchAlign v5.8 lane · 7 vs 3 public rows
Reading
Directional only

Instruction following

Directional only
Kimi K2.7 Code
76.6
#66/152
Sage-A1.5
91.9
#22/152
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Directional only

Reasoning

Not comparable
Kimi K2.7 Code
79.5
Unranked · 2 rankable rows
Sage-A1.5
80.6
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Kimi K2.7 Code
Not ranked
Sage-A1.5
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Kimi K2.7 Code
54.2
Estimated · #66/187
Sage-A1.5
Not ranked
Basis
BenchAlign v5.8 lane · 0 vs 1 public rows
Reading
Not comparable

Multilingual

Not comparable
Kimi K2.7 Code
Not ranked
Sage-A1.5
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Kimi K2.7 Code
58.3
Unranked · 2 rankable rows
Sage-A1.5
Not ranked
Basis
Provisional lane · 2 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

Kimi K2.7 Code
$0.00295
Fits in one request
Sage-A1.5
Self-hosted; infrastructure cost varies
Fits in one request

Sage-A1.5 has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Kimi K2.7 Code
$0.0595
Fits in one request
Sage-A1.5
Self-hosted; infrastructure cost varies
Fits in one request

Sage-A1.5 has no comparable published API token rate.

Cache-heavy agent loop

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

Kimi K2.7 Code
$0.097
Fits in one request
Sage-A1.5
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

Sage-A1.5 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.

API model ID

Kimi K2.7 Code

Not sourced

Sage-A1.5

Not sourced

Cached-input rate

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

Kimi K2.7 Code

$0.19 per 1M cached input tokens

Sage-A1.5

No comparable hosted API rate

InternScience Sage-A1.5 model card

Documented inputs

Kimi K2.7 Code

Not sourced

Sage-A1.5

Not sourced

Documented outputs

Kimi K2.7 Code

Not sourced

Sage-A1.5

Not sourced

Provider availability

Kimi K2.7 Code

Not sourced

Sage-A1.5

Not sourced

Reasoning profile

Kimi K2.7 Code

Reasoning

Sage-A1.5

Reasoning

Weight access

Kimi K2.7 Code

Open Weight

Sage-A1.5

Open Weight

License

Kimi K2.7 Code

Open Weight

Sage-A1.5

Open Weight

Release date

Kimi K2.7 Code

2026-06-12

Sage-A1.5

2026-10-15

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
Sage-A1.5 has the larger documented window (262K).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Kimi K2.7 Code or Sage-A1.5?

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, Kimi K2.7 Code or Sage-A1.5?

Sage-A1.5 scores higher for coding on the public lane, 54 to 41.7. Sage-A1.5 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, Kimi K2.7 Code or Sage-A1.5?

Sage-A1.5 scores higher for agentic tasks on the public lane, 57.7 to 38.5. Sage-A1.5 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, Kimi K2.7 Code or Sage-A1.5?

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, Kimi K2.7 Code or Sage-A1.5?

Sage-A1.5 has the larger documented context window: 262K, compared with 256K.

Self-host vs API cost

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

Kimi K2.7 Code
API / mo$3,713
Self-host / mo$27,962
Break-even500M/day
Sage-A1.5
API / mo$0
Self-host / mo$298
Break-even—
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 evidence25 rows

Agentic

  • Kimi Claw 24/7

    Kimi K2.7 Code46.9%
    Source
    Sage-A1.5—

    Not directly comparable

  • MCP Atlas

    Kimi K2.7 Code76%
    Source
    Sage-A1.5—

    Not directly comparable

  • MCP Mark Verified

    Kimi K2.7 Code81.1%
    Source
    Sage-A1.5—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Kimi K2.7 Code67.0%
    Source
    Sage-A1.5—

    Not directly comparable

  • GAIA

    Kimi K2.7 Code—
    Sage-A1.595.1%
    Source

    Not directly comparable

  • BrowseComp

    Kimi K2.7 Code—
    Sage-A1.581.7%
    Source

    Not directly comparable

  • MLE-Bench Lite

    Kimi K2.7 Code—
    Sage-A1.565.2%
    Source

    Not directly comparable

  • HLE w/ tools

    Kimi K2.7 Code—
    Sage-A1.555.1%
    Source

    Not directly comparable

  • VITA-Bench

    Kimi K2.7 Code—
    Sage-A1.545.4%
    Source

    Not directly comparable

  • PinchBench

    Kimi K2.7 Code—
    Sage-A1.590.0%
    Source

    Not directly comparable

Coding

  • Kimi Code Bench v2

    Kimi K2.7 Code62.0%
    Source
    Sage-A1.5—

    Not directly comparable

  • ProgramBench

    Kimi K2.7 Code53.6%
    Source
    Sage-A1.5—

    Not directly comparable

  • MLS-Bench Lite

    Kimi K2.7 Code35.1%
    Source
    Sage-A1.5—

    Not directly comparable

  • CursorBench 3.2

    Kimi K2.7 Code49.7%
    Source
    Sage-A1.5—

    Not directly comparable

  • OpenHarmony Bench

    Kimi K2.7 Code52.1%
    Source
    Sage-A1.5—

    Not directly comparable

  • LiveCodeBench (Vals)

    Kimi K2.7 Code82.1%
    Source
    Sage-A1.5—

    Not directly comparable

  • SWE-bench (Vals)

    Kimi K2.7 Code78.2%
    Source
    Sage-A1.5—

    Not directly comparable

  • SciCode

    Kimi K2.7 Code—
    Sage-A1.544.3%
    Source

    Not directly comparable

  • SWE-bench Pro

    Kimi K2.7 Code—
    Sage-A1.561.2%
    Source

    Not directly comparable

  • SWE Multilingual

    Kimi K2.7 Code—
    Sage-A1.572.7%
    Source

    Not directly comparable

Reasoning

  • CritPt

    Kimi K2.7 Code—
    Sage-A1.520.0%
    Source

    Not directly comparable

Knowledge

  • FrontierScience Research

    Kimi K2.7 Code—
    Sage-A1.548.3%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Kimi K2.7 Code—
    Sage-A1.581.6%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Kimi K2.7 Code54.035%
    Source
    Sage-A1.5—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Kimi K2.7 Code12.195%
    Source
    Sage-A1.5—

    Not directly comparable

25 public results · 0 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Kimi K2.7 Code vs Sage-A1.5

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