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 4.20

xAI

55.44/100

Estimated · Public rank #100

90% interval 38.5–72.3

Grok 4.20 vs Inkling

Updated August 29, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Thinking Machines Lab logo
Model B
Inkling

Thinking Machines Lab

67.02/100

Supported · Public rank #31

90% interval 60.0–74.0

Decision reading

Inkling has the higher public score estimate, 67.02 versus 55.44, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

7 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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Inkling

    Inkling leads on the same 2 weighted benchmark rows.

    Confidence: limited

  • 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

    Inkling

    Inkling 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
  • Cache-heavy agent loop cost

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

    Inkling

    Inkling 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.

    Confidence: rate-fallback

  • Repository review cost

    50K fresh input + 3K output tokens

    Inkling

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

    Confidence: listed-rates

  • 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.

Shared results
7
Grok 4.20 only
11
Inkling only
8
Like-for-like categories
2 / 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

Like-for-like
Grok 4.20
67.1
Inkling
68.6
Weighted basis
2 vs 2 rows
Reading
Inkling leads

Multimodal

Like-for-like
Grok 4.20
70.1
Inkling
76.5
Weighted basis
2 vs 2 rows
Reading
Inkling leads

Agentic

Directional only
Grok 4.20
47.1
Inkling
69.4
Weighted basis
1 vs 2 rows
Reading
Directional only

Reasoning

Not comparable
Grok 4.20
53.3
Inkling
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Grok 4.20
Not measured
Inkling
51.6
Weighted basis
0 vs 2 rows
Reading
Not comparable

Math

Not comparable
Grok 4.20
Not measured
Inkling
97.1
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
Grok 4.20
Not measured
Inkling
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Grok 4.20
Not measured
Inkling
79.8
Weighted basis
0 vs 1 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 4.20
$0.005
Fits in one request
Inkling
$0.00421
Fits in one request

Inkling 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
Inkling
$0.10754
Fits in one request

Inkling 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
Inkling
$0.159
Fits in one request

Inkling has the lower modeled cost

Grok 4.20 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

Inkling

1M

API model ID

Grok 4.20

Not sourced

Inkling

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

Inkling

$0.374 per 1M cached input tokens

Documented inputs

Grok 4.20

Not sourced

Inkling

Not sourced

Documented outputs

Grok 4.20

Not sourced

Inkling

Not sourced

Provider availability

Grok 4.20

Not sourced

Inkling

Not sourced

Reasoning profile

Grok 4.20

Reasoning

Inkling

Hybrid

Weight access

Grok 4.20

Proprietary

Inkling

Open Weight

License

Grok 4.20

Proprietary

Inkling

Open Weight

Release date

Grok 4.20

2026-03-10

Inkling

2026-07-15

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
Inkling has the higher public score estimate, 67.02 versus 55.44, but the 90% score intervals overlap.
Workload cost
Repository review: $0.118 vs $0.10754. Cache-heavy agent loop: $0.5 vs $0.159.
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 evidence26 rows

Agentic

  • Terminal-Bench 2.0

    Grok 4.2047.1%
    Source
    Inkling63.8%
    Source

    Inkling leads this result

  • DeepSearchQA

    Grok 4.2062.8%
    Source
    Inkling

    Not directly comparable

  • Gert Labs

    Grok 4.2038.36%
    Source
    Inkling

    Not directly comparable

  • BrowseComp

    Grok 4.20
    Inkling77.1%
    Source

    Not directly comparable

  • MCP Atlas

    Grok 4.20
    Inkling74.1%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pro

    Grok 4.2074.2%
    Source
    Inkling

    Not directly comparable

  • SWE-bench Verified

    Grok 4.2076.7%
    Source
    Inkling77.6%
    Source

    Inkling leads this result

  • SWE-bench Pro

    Grok 4.2051.8%
    Source
    Inkling54.3%
    Source

    Inkling leads this result

  • Vibe Code Bench

    Grok 4.204.06%
    Source
    Inkling

    Not directly comparable

  • Terminal-Bench 2.0

    Grok 4.20
    Inkling63.8%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Grok 4.2053.3%
    Source
    Inkling

    Not directly comparable

  • ARC-AGI-3

    Grok 4.200.1%
    Source
    Inkling

    Not directly comparable

Knowledge

  • GPQA-D

    Grok 4.2088.5%
    Source
    Inkling87.9%
    Source

    Grok 4.20 leads this result

  • HLE w/o tools

    Grok 4.2031.6%
    Source
    Inkling30%
    Source

    Grok 4.20 leads this result

  • HealthBench Hard

    Grok 4.2020.3%
    Source
    Inkling

    Not directly comparable

  • MedXpertQA (Text)

    Grok 4.2050.2%
    Source
    Inkling

    Not directly comparable

  • GPQA

    Grok 4.20
    Inkling87.9%
    Source

    Not directly comparable

  • HLE

    Grok 4.20
    Inkling46%
    Source

    Not directly comparable

Math

  • AIME26

    Grok 4.20
    Inkling97.1%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Grok 4.2075.2%
    Source
    Inkling73.5%
    Source

    Grok 4.20 leads this result

  • CharXiv

    Grok 4.2060.9%
    Source
    Inkling82%
    Source

    Inkling leads this result

  • ERQA

    Grok 4.2054.1%
    Source
    Inkling

    Not directly comparable

  • SimpleVQA

    Grok 4.2057.4%
    Source
    Inkling

    Not directly comparable

  • MedXpertQA (MM)

    Grok 4.2065.8%
    Source
    Inkling

    Not directly comparable

  • CharXiv w/o tools

    Grok 4.20
    Inkling78.1%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Grok 4.20
    Inkling79.8%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Grok 4.20 or Inkling?

Inkling has the higher public score estimate, 67.02 versus 55.44, 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 Inkling?

Inkling leads the like-for-like coding comparison across 2 shared weighted benchmark rows.

Which is better for agentic tasks, Grok 4.20 or Inkling?

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, Grok 4.20 or Inkling?

For the stated presets, chat costs $0.005 on Grok 4.20 and $0.00421 on Inkling; repository review costs $0.118 and $0.10754; the cache-heavy agent loop costs $0.5 and $0.159. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Grok 4.20 or Inkling?

Grok 4.20 has the larger documented context window: 2M, compared with 1M.

Related comparisons

Last updated August 29, 2026

Watch Grok 4.20 vs Inkling

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

Read a sample issue

Join 2,000+ readers.