Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
BenchLM
xAI logo
Model A
Grok 4.20

xAI

67.13/100

Supported · Public rank #31

90% interval 58.5–75.8

Grok 4.20 vs Kimi K2.5 (Reasoning)

Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Moonshot AI logo
Model B
Kimi K2.5 (Reasoning)

Moonshot AI

57/100

Estimated · Public rank #82

90% interval 45.5–68.5

Decision reading

Grok 4.20 has the higher public score estimate, 67.13 versus 57, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

5 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on XLinkedInSocial cardCSVJSON

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

    Grok 4.20

    Grok 4.20 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Kimi K2.5 (Reasoning)

    Kimi K2.5 (Reasoning) 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 K2.5 (Reasoning)

    Kimi K2.5 (Reasoning) has the lower estimated token cost for this stated workload. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) 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 K2.5 (Reasoning)

    Kimi K2.5 (Reasoning) 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

    Kimi K2.5 (Reasoning) 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

    Kimi K2.5 (Reasoning) is scored on Estimated evidence for agentic, so the reading is 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.

Shared results
5
Grok 4.20 only
18
Kimi K2.5 (Reasoning) only
4
Like-for-like categories
0 / 8

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign 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
Grok 4.20
26.7
Supported · #145/152
Kimi K2.5 (Reasoning)
48.2
Estimated · #65/152
Basis
BenchAlign lane · 4 vs 3 public rows
Reading
Directional only

Coding

Directional only
Grok 4.20
28.2
Supported · #141/151
Kimi K2.5 (Reasoning)
50.7
Estimated · #53/151
Basis
BenchAlign lane · 6 vs 2 public rows
Reading
Directional only

Knowledge

Directional only
Grok 4.20
49.4
Supported · #85/183
Kimi K2.5 (Reasoning)
50.7
Estimated · #75/183
Basis
BenchAlign lane · 6 vs 2 public rows
Reading
Directional only

Reasoning

Not comparable
Grok 4.20
34.2
Unranked · 2 rankable rows
Kimi K2.5 (Reasoning)
Not ranked
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Grok 4.20
Not ranked
Kimi K2.5 (Reasoning)
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Grok 4.20
Not ranked
Kimi K2.5 (Reasoning)
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Grok 4.20
34.6
#43/48
Kimi K2.5 (Reasoning)
63.2
Unranked · 1 rankable row
Basis
Provisional lane · 2 vs 1 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Grok 4.20
Not ranked
Kimi K2.5 (Reasoning)
Not ranked
Basis
Provisional lane · 0 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) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

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 4.20
$0.005
Fits in one request
Kimi K2.5 (Reasoning)
$0.0021
Fits in one request

Kimi K2.5 (Reasoning) has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Grok 4.20
$0.118
Fits in one request
Kimi K2.5 (Reasoning)
$0.039
Fits in one request

Kimi K2.5 (Reasoning) 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 4.20
$0.5
Fits in one request
Cached input priced at the published list-input rate
Kimi K2.5 (Reasoning)
$0.162
Fits in one request
Cached input priced at the published list-input rate

Kimi K2.5 (Reasoning) has the lower modeled cost

Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) 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 4.20

2M

Kimi K2.5 (Reasoning)

256K

API model ID

Grok 4.20

Not sourced

Kimi K2.5 (Reasoning)

Not sourced

Cached-input rate

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

Grok 4.20

Not published

Kimi K2.5 (Reasoning)

Not published

Documented inputs

Grok 4.20

Not sourced

Kimi K2.5 (Reasoning)

Not sourced

Documented outputs

Grok 4.20

Not sourced

Kimi K2.5 (Reasoning)

Not sourced

Provider availability

Grok 4.20

Not sourced

Kimi K2.5 (Reasoning)

Not sourced

Reasoning profile

Grok 4.20

Reasoning

Kimi K2.5 (Reasoning)

Reasoning

Weight access

Grok 4.20

Proprietary

Kimi K2.5 (Reasoning)

Proprietary

License

Grok 4.20

Proprietary

Kimi K2.5 (Reasoning)

Proprietary

Release date

Grok 4.20

2026-03-10

Kimi K2.5 (Reasoning)

2026-02-01

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
Grok 4.20 has the higher public score estimate, 67.13 versus 57, but the 90% score intervals overlap.
Workload cost
Repository review: $0.118 vs $0.039. Cache-heavy agent loop: $0.5 vs $0.162.
Context tradeoff
Grok 4.20 has the larger documented window (2M).

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 evidence27 rows

Agentic

  • Terminal-Bench 2.0

    Grok 4.2047.1%
    Source
    Kimi K2.5 (Reasoning)50.8%
    Source

    Kimi K2.5 (Reasoning) leads this result

  • DeepSearchQA

    Grok 4.2062.8%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • Gert Labs

    Shared source
    Grok 4.2038.36%
    Kimi K2.5 (Reasoning)32.58%

    Grok 4.20 leads this result

  • Terminal-Bench 2.1 (Vals)

    Grok 4.2044.2%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • BrowseComp

    Grok 4.20—
    Kimi K2.5 (Reasoning)60.6%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pro

    Grok 4.2074.2%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • SWE-bench Verified

    Grok 4.2076.7%
    Source
    Kimi K2.5 (Reasoning)76.8%
    Source

    Kimi K2.5 (Reasoning) leads this result

  • SWE-bench Pro

    Grok 4.2051.8%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • Vibe Code Bench

    Shared source
    Grok 4.204.06%
    Kimi K2.5 (Reasoning)17.54%

    Kimi K2.5 (Reasoning) leads this result

  • LiveCodeBench (Vals)

    Grok 4.2084.3%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • SWE-bench (Vals)

    Grok 4.2072.2%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Grok 4.2053.3%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • ARC-AGI-3

    Grok 4.200.1%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

Knowledge

  • GPQA-D

    Grok 4.2088.5%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • HLE w/o tools

    Grok 4.2031.6%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • HealthBench Hard

    Grok 4.2020.3%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • MedXpertQA (Text)

    Grok 4.2050.2%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • GPQA Diamond (Vals)

    Grok 4.2088.6%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • MMLU-Pro (Vals)

    Grok 4.2086.3%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • GPQA

    Grok 4.20—
    Kimi K2.5 (Reasoning)87.6%
    Source

    Not directly comparable

  • MMLU-Pro

    Grok 4.20—
    Kimi K2.5 (Reasoning)87.1%
    Source

    Not directly comparable

Math

  • AIME 2025

    Grok 4.20—
    Kimi K2.5 (Reasoning)96.1%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Grok 4.2075.2%
    Source
    Kimi K2.5 (Reasoning)78.5%
    Source

    Kimi K2.5 (Reasoning) leads this result

  • CharXiv

    Grok 4.2060.9%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • ERQA

    Grok 4.2054.1%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • SimpleVQA

    Grok 4.2057.4%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

  • MedXpertQA (MM)

    Grok 4.2065.8%
    Source
    Kimi K2.5 (Reasoning)—

    Not directly comparable

Frequently asked questions

Which is better, Grok 4.20 or Kimi K2.5 (Reasoning)?

Grok 4.20 has the higher public score estimate, 67.13 versus 57, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Grok 4.20 or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) scores higher for coding on the public lane, 50.7 to 28.2. Kimi K2.5 (Reasoning) 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, Grok 4.20 or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) scores higher for agentic tasks on the public lane, 48.2 to 26.7. Kimi K2.5 (Reasoning) 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, Grok 4.20 or Kimi K2.5 (Reasoning)?

For the stated presets, chat costs $0.005 on Grok 4.20 and $0.0021 on Kimi K2.5 (Reasoning); repository review costs $0.118 and $0.039; the cache-heavy agent loop costs $0.5 and $0.162. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Grok 4.20 or Kimi K2.5 (Reasoning)?

Grok 4.20 has the larger documented context window: 2M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 10, 2026

Watch Grok 4.20 vs Kimi K2.5 (Reasoning)

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

Read a sample issue

Join 2,000+ readers.