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
Anthropic logo
Model A
Claude Opus 4.5

Anthropic

63.78/100

Supported · Public rank #45

90% interval 49.8–77.8

Claude Opus 4.5 vs Kimi K2.6

Updated August 27, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Moonshot AI logo
Model B
Kimi K2.6

Moonshot AI

60.14/100

Estimated · Public rank #66

90% interval 50.3–70.0

Decision reading

Claude Opus 4.5 has the higher public score estimate, 63.78 versus 60.14, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

22 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

    Kimi K2.6

    Kimi K2.6 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Kimi K2.6

    Kimi K2.6 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    Kimi K2.6

    Kimi K2.6 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

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    Confidence: limited

  • 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. Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

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
22
Claude Opus 4.5 only
23
Kimi K2.6 only
10
Like-for-like categories
2 / 8

3 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

Math

Like-for-like
Claude Opus 4.5
57.5
Kimi K2.6
67.1
Weighted basis
4 vs 4 rows
Reading
Kimi K2.6 leads

Multimodal

Like-for-like
Claude Opus 4.5
69.9
Kimi K2.6
79.8
Weighted basis
2 vs 2 rows
Reading
Kimi K2.6 leads

Agentic

Directional only
Claude Opus 4.5
62.6
Kimi K2.6
73.5
Weighted basis
2 vs 3 rows
Reading
Directional only

Coding

Directional only
Claude Opus 4.5
71.7
Kimi K2.6
64.4
Weighted basis
2 vs 3 rows
Reading
Directional only

Knowledge

Directional only
Claude Opus 4.5
58.1
Kimi K2.6
42.2
Weighted basis
4 vs 2 rows
Reading
Directional only

Reasoning

Not comparable
Claude Opus 4.5
64.4
Kimi K2.6
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 4.5
85.7
Kimi K2.6
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Opus 4.5
69.5
Kimi K2.6
Not measured
Weighted basis
2 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.

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.

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 Opus 4.5
$0.0175
Fits in one request
Kimi K2.6
$0.00295
Fits in one request

Kimi K2.6 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Opus 4.5
$0.325
Fits in one request
Kimi K2.6
$0.0595
Fits in one request

Kimi K2.6 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 Opus 4.5
$1.35
Does not fit in one request
Cached input priced at the published list-input rate
Kimi K2.6
$0.249
Fits in one request
Cached input priced at the published list-input rate

Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.6 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.

Context window

Maximum documented context; output-token limits may be lower.

Claude Opus 4.5

200K

Kimi K2.6

256K

API model ID

Claude Opus 4.5

Not sourced

Kimi K2.6

Not sourced

Cached-input rate

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

Claude Opus 4.5

Not published

Kimi K2.6

Not published

Documented inputs

Claude Opus 4.5

Not sourced

Kimi K2.6

Not sourced

Documented outputs

Claude Opus 4.5

Not sourced

Kimi K2.6

Not sourced

Provider availability

Claude Opus 4.5

Not sourced

Kimi K2.6

Not sourced

Reasoning profile

Claude Opus 4.5

Non-Reasoning

Kimi K2.6

Reasoning

Weight access

Claude Opus 4.5

Proprietary

Kimi K2.6

Open Weight

License

Claude Opus 4.5

Proprietary

Kimi K2.6

Open Weight

Release date

Claude Opus 4.5

2025-11-01

Kimi K2.6

2026-04-20

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 Opus 4.5 has the higher public score estimate, 63.78 versus 60.14, but the 90% score intervals overlap.
Workload cost
Repository review: $0.325 vs $0.0595. Cache-heavy agent loop: $1.35 vs $0.249.
Context tradeoff
Kimi K2.6 has the larger documented window (256K).

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 Opus 4.5
API / mo$22,500
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.6
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 evidence55 rows

Agentic

  • Terminal-Bench 2.0

    Claude Opus 4.559.3%
    Source
    Kimi K2.666.7%
    Source

    Kimi K2.6 leads this result

  • OSWorld-Verified

    Claude Opus 4.566.3%
    Source
    Kimi K2.673.1%
    Source

    Kimi K2.6 leads this result

  • OSWorld

    Claude Opus 4.566.3%
    Source
    Kimi K2.6—

    Not directly comparable

  • Claw-Eval

    Claude Opus 4.559.6%
    Source
    Kimi K2.662.3%
    Source

    Kimi K2.6 leads this result

  • QwenClawBench

    Claude Opus 4.552.3%
    Source
    Kimi K2.6—

    Not directly comparable

  • τ³-bench results

    Claude Opus 4.570.2%
    Source
    Kimi K2.6—

    Not directly comparable

  • VITA-Bench

    Claude Opus 4.523.3%
    Source
    Kimi K2.6—

    Not directly comparable

  • DeepPlanning

    Claude Opus 4.526.4%
    Source
    Kimi K2.6—

    Not directly comparable

  • Toolathlon

    Claude Opus 4.543.5%
    Source
    Kimi K2.650%
    Source

    Kimi K2.6 leads this result

  • MCP Atlas

    Claude Opus 4.542.3%
    Source
    Kimi K2.655.9%
    Source

    Kimi K2.6 leads this result

  • MCP-Tasks

    Claude Opus 4.571.8%
    Source
    Kimi K2.6—

    Not directly comparable

  • WideResearch

    Claude Opus 4.576.4%
    Source
    Kimi K2.680.8%
    Source

    Kimi K2.6 leads this result

  • CyberGym

    Claude Opus 4.550.6%
    Source
    Kimi K2.6—

    Not directly comparable

  • Gert Labs

    Shared source
    Claude Opus 4.564.23%
    Kimi K2.656.82%

    Claude Opus 4.5 leads this result

  • JobBench

    Claude Opus 4.532.3%
    Source
    Kimi K2.6—

    Not directly comparable

  • BrowseComp

    Claude Opus 4.5—
    Kimi K2.683.2%
    Source

    Not directly comparable

  • DeepSearchQA

    Claude Opus 4.5—
    Kimi K2.692.5%
    Source

    Not directly comparable

  • ResearchClawBench

    Claude Opus 4.5—
    Kimi K2.618.0%
    Source

    Not directly comparable

  • OSWorld 2.0

    Claude Opus 4.5—
    Kimi K2.64.6%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Opus 4.580.9%
    Source
    Kimi K2.680.2%
    Source

    Claude Opus 4.5 leads this result

  • LiveCodeBench v6

    Claude Opus 4.584.8%
    Source
    Kimi K2.689.6%
    Source

    Kimi K2.6 leads this result

  • SWE-bench Pro

    Claude Opus 4.557.1%
    Source
    Kimi K2.658.6%
    Source

    Kimi K2.6 leads this result

  • SWE Multilingual

    Claude Opus 4.577.5%
    Source
    Kimi K2.676.7%
    Source

    Claude Opus 4.5 leads this result

  • NL2Repo

    Claude Opus 4.543.2%
    Source
    Kimi K2.6—

    Not directly comparable

  • SciCode

    Claude Opus 4.5—
    Kimi K2.652.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Opus 4.5—
    Kimi K2.666.7%
    Source

    Not directly comparable

  • Vibe Code Bench

    Claude Opus 4.5—
    Kimi K2.637.89%
    Source

    Not directly comparable

  • cursorBench31

    Claude Opus 4.5—
    Kimi K2.647.6%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Claude Opus 4.564.4%
    Source
    Kimi K2.6—

    Not directly comparable

  • AI-Needle

    Claude Opus 4.574%
    Source
    Kimi K2.6—

    Not directly comparable

Knowledge

  • GPQA

    Claude Opus 4.587%
    Source
    Kimi K2.690.5%
    Source

    Kimi K2.6 leads this result

  • SuperGPQA

    Claude Opus 4.570.6%
    Source
    Kimi K2.6—

    Not directly comparable

  • MMLU-Pro

    Claude Opus 4.589.5%
    Source
    Kimi K2.6—

    Not directly comparable

  • MMLU-Redux

    Claude Opus 4.596.6%
    Source
    Kimi K2.6—

    Not directly comparable

  • C-Eval

    Claude Opus 4.592.2%
    Source
    Kimi K2.6—

    Not directly comparable

  • HLE

    Claude Opus 4.530.8%
    Source
    Kimi K2.634.7%
    Source

    Kimi K2.6 leads this result

  • GPQA-D

    Claude Opus 4.5—
    Kimi K2.690.5%
    Source

    Not directly comparable

Math

  • AIME26

    Claude Opus 4.595.1%
    Source
    Kimi K2.696.4%
    Source

    Kimi K2.6 leads this result

  • HMMT Feb 2025

    Claude Opus 4.592.9%
    Source
    Kimi K2.6—

    Not directly comparable

  • HMMT Nov 2025

    Claude Opus 4.593.3%
    Source
    Kimi K2.6—

    Not directly comparable

  • HMMT Feb 2026

    Claude Opus 4.585.3%
    Source
    Kimi K2.692.7%
    Source

    Kimi K2.6 leads this result

  • MMAnswerBench

    Claude Opus 4.584.0%
    Source
    Kimi K2.686.0%
    Source

    Kimi K2.6 leads this result

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Opus 4.520.690%
    Kimi K2.638.966%

    Kimi K2.6 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Opus 4.54.167%
    Kimi K2.614.580%

    Kimi K2.6 leads this result

Multilingual

  • MMLU-ProX

    Claude Opus 4.585.7%
    Source
    Kimi K2.6—

    Not directly comparable

  • NOVA-63

    Claude Opus 4.556.7%
    Source
    Kimi K2.6—

    Not directly comparable

Multimodal

  • MMMU-Pro

    Claude Opus 4.570.6%
    Source
    Kimi K2.679.4%
    Source

    Kimi K2.6 leads this result

  • MathVision

    Claude Opus 4.574.3%
    Source
    Kimi K2.687.4%
    Source

    Kimi K2.6 leads this result

  • CharXiv

    Claude Opus 4.568.5%
    Source
    Kimi K2.680.4%
    Source

    Kimi K2.6 leads this result

  • VideoMMMU

    Claude Opus 4.584.4%
    Source
    Kimi K2.6—

    Not directly comparable

  • ScreenSpot Pro

    Claude Opus 4.545.7%
    Source
    Kimi K2.6—

    Not directly comparable

  • V*

    Claude Opus 4.567.0%
    Source
    Kimi K2.696.9%
    Source

    Kimi K2.6 leads this result

  • MMMU-Pro w/ Python

    Claude Opus 4.5—
    Kimi K2.680.1%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Claude Opus 4.590.9%
    Source
    Kimi K2.6—

    Not directly comparable

  • IFBench

    Claude Opus 4.558%
    Source
    Kimi K2.6—

    Not directly comparable

Frequently asked questions

Which is better, Claude Opus 4.5 or Kimi K2.6?

Claude Opus 4.5 has the higher public score estimate, 63.78 versus 60.14, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Claude Opus 4.5 or Kimi K2.6?

The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Claude Opus 4.5 or Kimi K2.6?

The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Claude Opus 4.5 or Kimi K2.6?

For the stated presets, chat costs $0.0175 on Claude Opus 4.5 and $0.00295 on Kimi K2.6; repository review costs $0.325 and $0.0595; the cache-heavy agent loop costs $1.35 and $0.249. Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Opus 4.5 or Kimi K2.6?

Kimi K2.6 has the larger documented context window: 256K, compared with 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 27, 2026

Watch Claude Opus 4.5 vs Kimi K2.6

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

Read a sample issue

Join 2,000+ readers.