Model A

Anthropic

68.0/100

Supported · Public rank #23

90% interval 54.8–81.3

Claude Opus 4.6 vs Kimi K3

Updated August 19, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B

Kimi K3

Moonshot AI

80.5/100

Supported · Public rank #5

90% interval 77.7–83.4

Decision reading

Kimi K3 has the higher public score estimate, 80.53 versus 68, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

9 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 K3
Kimi K3 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Kimi K3
Kimi K3 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 K3
Kimi K3 has the lower estimated token cost for this stated workload. Claude Opus 4.6 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 K3
Kimi K3 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
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
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.

24 Claude Opus 4.6 only

9 Shared

31 Kimi K3 only

Shared results: 9
Claude Opus 4.6 only: 24
Kimi K3 only: 31
Like-for-like categories: 0 / 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.

Agentic

Directional only

Claude Opus 4.6: 73.0
Kimi K3: 89.5
Weighted basis: 3 vs 2 rows
Reading: Directional only

Knowledge

Directional only

Claude Opus 4.6: 69.1
Kimi K3: 61.0
Weighted basis: 4 vs 2 rows
Reading: Directional only

Multimodal

Directional only

Claude Opus 4.6: 77.3
Kimi K3: 78.5
Weighted basis: 1 vs 3 rows
Reading: Directional only

Coding

Not comparable

Claude Opus 4.6: 68.1
Kimi K3: Not measured
Weighted basis: 3 vs 0 rows
Reading: Not comparable

Reasoning

Not comparable

Claude Opus 4.6: Not measured
Kimi K3: Not measured
Weighted basis: 0 vs 0 rows
Reading: Not comparable

Math

Not comparable

Claude Opus 4.6: 36.3
Kimi K3: Not measured
Weighted basis: 2 vs 0 rows
Reading: Not comparable

Multilingual

Not comparable

Claude Opus 4.6: Not measured
Kimi K3: Not measured
Weighted basis: 0 vs 0 rows
Reading: Not comparable

Instruction following

Not comparable

Claude Opus 4.6: Not measured
Kimi K3: Not measured
Weighted basis: 0 vs 0 rows
Reading: Not comparable

Category averages with the server-provided evidence basis for Claude Opus 4.6 and Kimi K3
Category	Claude Opus 4.6	Kimi K3	Weighted basis	Reading
Agentic	73.0	89.5	Directional only3 vs 2 rows	Directional only
Knowledge	69.1	61.0	Directional only4 vs 2 rows	Directional only
Multimodal	77.3	78.5	Directional only1 vs 3 rows	Directional only
Coding	68.1	Not measured	Not comparable3 vs 0 rows	Not comparable
Reasoning	Not measured	Not measured	Not comparable0 vs 0 rows	Not comparable
Math	36.3	Not measured	Not comparable2 vs 0 rows	Not comparable
Multilingual	Not measured	Not measured	Not comparable0 vs 0 rows	Not comparable
Instruction following	Not measured	Not measured	Not comparable0 vs 0 rows	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.

Terminal-Bench 2.0
Agentic
Claude Opus 4.6: 65.4%Kimi K3: 88.3%Normalized gap 22.9Claude Opus 4.6 source Kimi K3 source
BrowseComp
Agentic
Claude Opus 4.6: 83.7%Kimi K3: 91.2%Normalized gap 7.5Claude Opus 4.6 source Kimi K3 source
MMMU-Pro
Multimodal
Claude Opus 4.6: 77.3%Kimi K3: 81.6%Normalized gap 4.3Claude Opus 4.6 source Kimi K3 source
HLE
Knowledge
Claude Opus 4.6: 53%Kimi K3: 56%Normalized gap 3.0Claude Opus 4.6 source Kimi K3 source
GPQA
Knowledge
Claude Opus 4.6: 91.3%Kimi K3: 93.5%Normalized gap 2.2Claude Opus 4.6 source Kimi K3 source

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 4.6: $0.0175; Fits in one request
Kimi K3: $0.0105; Fits in one request

Kimi K3 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Opus 4.6: $0.325; Fits in one request
Kimi K3: $0.195; Fits in one request

Kimi K3 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 4.6: $1.35; Fits in one request; Cached input priced at the published list-input rate
Kimi K3: $0.27; Fits in one request

Kimi K3 has the lower modeled cost

Claude Opus 4.6 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.

SpecificationClaude Opus 4.6Kimi K3

Context window

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

Claude Opus 4.6

Kimi K3

1.05M

API model ID

Claude Opus 4.6

Not sourced

Kimi K3

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 4.6

Not published

Kimi K3

$0.3 per 1M cached input tokens

Documented inputs

Claude Opus 4.6

Not sourced

Kimi K3

Not sourced

Documented outputs

Claude Opus 4.6

Not sourced

Kimi K3

Not sourced

Provider availability

Claude Opus 4.6

Not sourced

Kimi K3

Not sourced

Reasoning profile

Claude Opus 4.6

Non-Reasoning

Kimi K3

Reasoning

Weight access

Claude Opus 4.6

Proprietary

Kimi K3

Pending

License

Claude Opus 4.6

Proprietary

Kimi K3

Pending

Release date

Claude Opus 4.6

2026-02-01

Kimi K3

2026-07-16

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: Kimi K3 has the higher public score estimate, 80.53 versus 68, but the 90% score intervals overlap.
Workload cost: Repository review: $0.325 vs $0.195. Cache-heavy agent loop: $1.35 vs $0.27.
Context tradeoff: Kimi K3 has the larger documented window (1.05M).

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

Benchmark evidence

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

Browse raw public benchmark evidence64 rows

Agentic

Terminal-Bench 2.0
Claude Opus 4.665.4%
Source
Kimi K388.3%
Source
Kimi K3 leads this result
BrowseComp
Claude Opus 4.683.7%
Source
Kimi K391.2%
Source
Kimi K3 leads this result
OSWorld-Verified
Claude Opus 4.672.7%
Source
Kimi K3—
Not directly comparable
Claw-Eval
Claude Opus 4.670.4%
Source
Kimi K3—
Not directly comparable
DeepSearchQA
Claude Opus 4.673.7%
Source
Kimi K395.0%
Source
Kimi K3 leads this result
CyberGym
Claude Opus 4.666.6%
Source
Kimi K3—
Not directly comparable
Gert Labs
Claude Opus 4.661.85%
Source
Kimi K3—
Not directly comparable
ResearchClawBench
Claude Opus 4.619.9%
Source
Kimi K3—
Not directly comparable
JobBench
Claude Opus 4.636.7%
Source
Kimi K352.9%
Source
Kimi K3 leads this result
Toolathlon-Verified
Claude Opus 4.6—
Kimi K373.2%
Source
Not directly comparable
MCP Atlas
Claude Opus 4.6—
Kimi K384.2%
Source
Not directly comparable
AutomationBench
Claude Opus 4.6—
Kimi K330.8%
Source
Not directly comparable
APEX-Agents
Claude Opus 4.6—
Kimi K337.6%
Source
Not directly comparable
SpreadsheetBench 2
Claude Opus 4.6—
Kimi K334.8%
Source
Not directly comparable
DECK-Bench
Claude Opus 4.6—
Kimi K373.5%
Source
Not directly comparable

Coding

SWE-bench Verified
Claude Opus 4.680.8%
Source
Kimi K3—
Not directly comparable
SWE-bench Verified*
Claude Opus 4.675.6%
Source
Kimi K3—
Not directly comparable
LiveCodeBench Pro
Claude Opus 4.670.7%
Source
Kimi K3—
Not directly comparable
SWE-bench Pro
Claude Opus 4.653.4%
Source
Kimi K3—
Not directly comparable
SWE-Rebench
Claude Opus 4.665.3%
Source
Kimi K3—
Not directly comparable
React Native Evals
Claude Opus 4.684.1%
Source
Kimi K3—
Not directly comparable
Vibe Code Bench
Claude Opus 4.657.57%
Source
Kimi K3—
Not directly comparable
FrontierCode 1.1 Main
Claude Opus 4.626.9%
Source
Kimi K3—
Not directly comparable
deepSwe
Claude Opus 4.6—
Kimi K367.5%
Source
Not directly comparable
cursorBench32
Claude Opus 4.6—
Kimi K360.8%
Source
Not directly comparable
FrontierSWE
Claude Opus 4.6—
Kimi K381.2%
Source
Not directly comparable
ProgramBench
Claude Opus 4.6—
Kimi K377.8%
Source
Not directly comparable
Kimi Code Bench v2
Claude Opus 4.6—
Kimi K372.9%
Source
Not directly comparable
sweMarathon
Claude Opus 4.6—
Kimi K342%
Source
Not directly comparable
PostTrain Bench
Claude Opus 4.6—
Kimi K336.6%
Source
Not directly comparable
MLS-Bench Lite
Claude Opus 4.6—
Kimi K348.3%
Source
Not directly comparable
VulcanBench v3
Claude Opus 4.6—
Kimi K373.9%
Source
Not directly comparable
APEX-SWE
Claude Opus 4.6—
Kimi K348.0%
Source
Not directly comparable
EEBench
Claude Opus 4.6—
Kimi K338.3%
Source
Not directly comparable
InferenceEval
Claude Opus 4.6—
Kimi K339.8%
Source
Not directly comparable
KernelBench Internal
Claude Opus 4.6—
Kimi K368.5%
Source
Not directly comparable

Knowledge

GPQA
Claude Opus 4.691.3%
Source
Kimi K393.5%
Source
Kimi K3 leads this result
GPQA-D
Claude Opus 4.689.2%
Source
Kimi K393.5%
Source
Kimi K3 leads this result
SuperGPQA
Claude Opus 4.695%
Source
Kimi K3—
Not directly comparable
MMLU-Pro
Claude Opus 4.682%
Source
Kimi K3—
Not directly comparable
MMLU-Pro (Arcee)
Claude Opus 4.689.1%
Source
Kimi K3—
Not directly comparable
HLE
Claude Opus 4.653%
Source
Kimi K356%
Source
Kimi K3 leads this result
HLE w/o tools
Claude Opus 4.640%
Source
Kimi K343.5%
Source
Kimi K3 leads this result
HealthBench Hard
Claude Opus 4.614.8%
Source
Kimi K3—
Not directly comparable
MedXpertQA (Text)
Claude Opus 4.652.1%
Source
Kimi K3—
Not directly comparable

Math

AIME25 (Arcee)
Claude Opus 4.699.8%
Source
Kimi K3—
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Opus 4.640.700%
Source
Kimi K3—
Not directly comparable
FrontierMath v2 (Tier 4)
Claude Opus 4.622.900%
Source
Kimi K3—
Not directly comparable

Multimodal

MMMU-Pro
Claude Opus 4.677.3%
Source
Kimi K381.6%
Source
Kimi K3 leads this result
ERQA
Claude Opus 4.651.6%
Source
Kimi K3—
Not directly comparable
ScreenSpot Pro
Claude Opus 4.683.1%
Source
Kimi K3—
Not directly comparable
MedXpertQA (MM)
Claude Opus 4.664.8%
Source
Kimi K3—
Not directly comparable
OfficeQA Pro
Claude Opus 4.6—
Kimi K363.3%
Source
Not directly comparable
MMMU-Pro w/ Python
Claude Opus 4.6—
Kimi K383.4%
Source
Not directly comparable
CharXiv w/o tools
Claude Opus 4.6—
Kimi K384.8%
Source
Not directly comparable
CharXiv
Claude Opus 4.6—
Kimi K391.3%
Source
Not directly comparable
MathVision
Claude Opus 4.6—
Kimi K394.3%
Source
Not directly comparable
MathVision w/ Python
Claude Opus 4.6—
Kimi K397.8%
Source
Not directly comparable
BabyVision w/ Python
Claude Opus 4.6—
Kimi K385.7%
Source
Not directly comparable
ZeroBench
Claude Opus 4.6—
Kimi K323.0%
Source
Not directly comparable
ZeroBench w/ Python
Claude Opus 4.6—
Kimi K341.0%
Source
Not directly comparable
WorldVQA ForceAnswer
Claude Opus 4.6—
Kimi K351.0%
Source
Not directly comparable
OmniDocBench
Claude Opus 4.6—
Kimi K391.1%
Source
Not directly comparable
PerceptionBench
Claude Opus 4.6—
Kimi K358.5%
Source
Not directly comparable

Frequently asked questions

Which is better, Claude Opus 4.6 or Kimi K3?

Kimi K3 has the higher public score estimate, 80.53 versus 68, 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 4.6 or Kimi K3?

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 Opus 4.6 or Kimi K3?

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 4.6 or Kimi K3?

For the stated presets, chat costs $0.0175 on Claude Opus 4.6 and $0.0105 on Kimi K3; repository review costs $0.325 and $0.195; the cache-heavy agent loop costs $1.35 and $0.27. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Opus 4.6 or Kimi K3?

Kimi K3 has the larger documented context window: 1.05M, compared with 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 19, 2026

Watch Claude Opus 4.6 vs Kimi K3

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

Read a sample issue

Join 2,000+ readers.

Claude Opus 4.6 vs Kimi K3

Which one for your work

Long documents

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Coding work

Agentic work

What is actually comparable

Category results, on a stated basis

Agentic

Knowledge

Multimodal

Coding

Reasoning

Math

Multilingual

Instruction following

Shape of the matched evidence

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

Benchmark evidence

Agentic

Coding

Knowledge

Math

Multimodal

Frequently asked questions

Which is better, Claude Opus 4.6 or Kimi K3?

Which is better for coding, Claude Opus 4.6 or Kimi K3?

Which is better for agentic tasks, Claude Opus 4.6 or Kimi K3?

Which costs less, Claude Opus 4.6 or Kimi K3?

Which has the larger context window, Claude Opus 4.6 or Kimi K3?

Related comparisons

Watch Claude Opus 4.6 vs Kimi K3