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
xAI logo
Model A
Grok Code Fast 1

xAI

37.87/100

Supported · Public rank #206

90% interval 34.9–40.9

Grok Code Fast 1 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

Kimi K2.6 has the higher public score, 60.14 versus 37.87, and the 90% score intervals do not overlap.

1 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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    Grok Code Fast 1

    Grok Code Fast 1 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

    Grok Code Fast 1

    Grok Code Fast 1 has the lower estimated token cost for this stated workload. Grok Code Fast 1 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

Show secondary and unsupported calls
  • Repository review cost

    50K fresh input + 3K output tokens

    Grok Code Fast 1

    Grok Code Fast 1 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

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

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
1
Grok Code Fast 1 only
0
Kimi K2.6 only
31
Like-for-like categories
0 / 8

1 category uses 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.

Coding

Directional only
Grok Code Fast 1
70.8
Kimi K2.6
64.4
Weighted basis
1 vs 3 rows
Reading
Directional only

Agentic

Not comparable
Grok Code Fast 1
Not measured
Kimi K2.6
73.5
Weighted basis
0 vs 3 rows
Reading
Not comparable

Reasoning

Not comparable
Grok Code Fast 1
Not measured
Kimi K2.6
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Grok Code Fast 1
Not measured
Kimi K2.6
42.2
Weighted basis
0 vs 2 rows
Reading
Not comparable

Math

Not comparable
Grok Code Fast 1
Not measured
Kimi K2.6
67.1
Weighted basis
0 vs 4 rows
Reading
Not comparable

Multilingual

Not comparable
Grok Code Fast 1
Not measured
Kimi K2.6
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Grok Code Fast 1
Not measured
Kimi K2.6
79.8
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
Grok Code Fast 1
Not measured
Kimi K2.6
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.

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

Grok Code Fast 1
$0.00095
Fits in one request
Kimi K2.6
$0.00295
Fits in one request

Grok Code Fast 1 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Grok Code Fast 1
$0.0145
Fits in one request
Kimi K2.6
$0.0595
Fits in one request

Grok Code Fast 1 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Grok Code Fast 1
$0.059
Fits 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

Grok Code Fast 1 has the lower modeled cost

Grok Code Fast 1 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.

Grok Code Fast 1

256K

Kimi K2.6

256K

API model ID

Grok Code Fast 1

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.

Grok Code Fast 1

Not published

Kimi K2.6

Not published

Documented inputs

Grok Code Fast 1

Not sourced

Kimi K2.6

Not sourced

Documented outputs

Grok Code Fast 1

Not sourced

Kimi K2.6

Not sourced

Provider availability

Grok Code Fast 1

Not sourced

Kimi K2.6

Not sourced

Reasoning profile

Grok Code Fast 1

Non-Reasoning

Kimi K2.6

Reasoning

Weight access

Grok Code Fast 1

Proprietary

Kimi K2.6

Open Weight

License

Grok Code Fast 1

Proprietary

Kimi K2.6

Open Weight

Release date

Grok Code Fast 1

2025-08-28

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
Kimi K2.6 has the higher public score, 60.14 versus 37.87, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.0145 vs $0.0595. Cache-heavy agent loop: $0.059 vs $0.249.
Context tradeoff
Both models list 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.

Grok Code Fast 1
API / mo$1,275
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 evidence32 rows

Agentic

  • Terminal-Bench 2.0

    Grok Code Fast 1
    Kimi K2.666.7%
    Source

    Not directly comparable

  • BrowseComp

    Grok Code Fast 1
    Kimi K2.683.2%
    Source

    Not directly comparable

  • OSWorld-Verified

    Grok Code Fast 1
    Kimi K2.673.1%
    Source

    Not directly comparable

  • Toolathlon

    Grok Code Fast 1
    Kimi K2.650%
    Source

    Not directly comparable

  • MCP Atlas

    Grok Code Fast 1
    Kimi K2.655.9%
    Source

    Not directly comparable

  • Claw-Eval

    Grok Code Fast 1
    Kimi K2.662.3%
    Source

    Not directly comparable

  • DeepSearchQA

    Grok Code Fast 1
    Kimi K2.692.5%
    Source

    Not directly comparable

  • WideResearch

    Grok Code Fast 1
    Kimi K2.680.8%
    Source

    Not directly comparable

  • Gert Labs

    Grok Code Fast 1
    Kimi K2.656.82%
    Source

    Not directly comparable

  • ResearchClawBench

    Grok Code Fast 1
    Kimi K2.618.0%
    Source

    Not directly comparable

  • OSWorld 2.0

    Grok Code Fast 1
    Kimi K2.64.6%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Grok Code Fast 170.8%
    Source
    Kimi K2.680.2%
    Source

    Kimi K2.6 leads this result

  • LiveCodeBench v6

    Grok Code Fast 1
    Kimi K2.689.6%
    Source

    Not directly comparable

  • SWE-bench Pro

    Grok Code Fast 1
    Kimi K2.658.6%
    Source

    Not directly comparable

  • SWE Multilingual

    Grok Code Fast 1
    Kimi K2.676.7%
    Source

    Not directly comparable

  • SciCode

    Grok Code Fast 1
    Kimi K2.652.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Grok Code Fast 1
    Kimi K2.666.7%
    Source

    Not directly comparable

  • Vibe Code Bench

    Grok Code Fast 1
    Kimi K2.637.89%
    Source

    Not directly comparable

  • cursorBench31

    Grok Code Fast 1
    Kimi K2.647.6%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Grok Code Fast 1
    Kimi K2.690.5%
    Source

    Not directly comparable

  • GPQA-D

    Grok Code Fast 1
    Kimi K2.690.5%
    Source

    Not directly comparable

  • HLE

    Grok Code Fast 1
    Kimi K2.634.7%
    Source

    Not directly comparable

Math

  • AIME26

    Grok Code Fast 1
    Kimi K2.696.4%
    Source

    Not directly comparable

  • HMMT Feb 2026

    Grok Code Fast 1
    Kimi K2.692.7%
    Source

    Not directly comparable

  • MMAnswerBench

    Grok Code Fast 1
    Kimi K2.686.0%
    Source

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Grok Code Fast 1
    Kimi K2.638.966%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Grok Code Fast 1
    Kimi K2.614.580%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Grok Code Fast 1
    Kimi K2.679.4%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    Grok Code Fast 1
    Kimi K2.680.1%
    Source

    Not directly comparable

  • CharXiv

    Grok Code Fast 1
    Kimi K2.680.4%
    Source

    Not directly comparable

  • MathVision

    Grok Code Fast 1
    Kimi K2.687.4%
    Source

    Not directly comparable

  • V*

    Grok Code Fast 1
    Kimi K2.696.9%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Grok Code Fast 1 or Kimi K2.6?

Kimi K2.6 has the higher public score, 60.14 versus 37.87, 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, Grok Code Fast 1 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, Grok Code Fast 1 or Kimi K2.6?

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, Grok Code Fast 1 or Kimi K2.6?

For the stated presets, chat costs $0.00095 on Grok Code Fast 1 and $0.00295 on Kimi K2.6; repository review costs $0.0145 and $0.0595; the cache-heavy agent loop costs $0.059 and $0.249. Grok Code Fast 1 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, Grok Code Fast 1 or Kimi K2.6?

Both models list the same context window, 256K.

Related comparisons

Last updated August 27, 2026

Watch Grok Code Fast 1 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.