Skip to main content
BenchLM

Grok 4.6 vs MiMo-V2.5-Pro

Updated September 25, 2026. Rank says Grok 4.6 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInSocial cardCSVJSON

Decision reading

Grok 4.6 has the higher public score estimate, 69.19 versus 52.03, 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.

Model A
xAI logo

xAI

69.19/100

Supported · Public rank #15

90% interval 66.3–72.1

Model B
Xiaomi logo

Xiaomi

52.03/100

Supported · Public rank #68

90% interval 36.0–68.1

Shared results
5
Grok 4.6 only
12
MiMo-V2.5-Pro only
8
Like-for-like categories
3 / 8
Supported: Grok 4.6 and MiMo-V2.5-ProHow the comparison works

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

    Grok 4.6

    Grok 4.6 leads on the public coding lane, 62 to 45.7, with Supported evidence for both models, although the 90% intervals overlap.

    Confidence: limited
  • Agentic work

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

    Grok 4.6

    Grok 4.6 leads on the public agentic lane, 67.9 to 37.5, with Supported evidence for both models and non-overlapping 90% intervals.

    Confidence: stronger
  • Long documents

    Prompts that approach the documented context limit

    MiMo-V2.5-Pro

    MiMo-V2.5-Pro has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls
  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Cache-heavy agent loop cost

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

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

62.0Grok 4.645.7MiMo-V2.5-Pro

Like-for-like · BenchAlign v5.7

Grok 4.6 leads the like-for-like coding row, although the 90% intervals overlap.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

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.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.7 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

Like-for-like
Grok 4.6
67.9
Supported · #8/105
MiMo-V2.5-Pro
37.5
Supported · #48/105
Basis
BenchAlign v5.7 lane · 4 vs 5 public rows
Reading
Grok 4.6 leads

Coding

Like-for-like
Grok 4.6
62.0
Supported · #14/135
MiMo-V2.5-Pro
45.7
Supported · #46/135
Basis
BenchAlign v5.7 lane · 8 vs 4 public rows
Reading
Grok 4.6 leads · intervals overlap

Knowledge

Like-for-like
Grok 4.6
69.0
Supported · #13/158
MiMo-V2.5-Pro
49.8
Supported · #57/158
Basis
BenchAlign v5.7 lane · 2 vs 4 public rows
Reading
Grok 4.6 leads · intervals overlap

Reasoning

Not comparable
Grok 4.6
57.6
#16/19
MiMo-V2.5-Pro
76.8
Unranked · 2 rankable rows
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Grok 4.6
Not ranked
MiMo-V2.5-Pro
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Grok 4.6
Not ranked
MiMo-V2.5-Pro
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Grok 4.6
Not ranked
MiMo-V2.5-Pro
92.4
#6/124
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Grok 4.6
Not ranked
MiMo-V2.5-Pro
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 v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

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 4.6
$0.005
Fits in one request
MiMo-V2.5-Pro
API rate not published
Fits in one request

MiMo-V2.5-Pro has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Grok 4.6
$0.118
Fits in one request
MiMo-V2.5-Pro
API rate not published
Fits in one request

MiMo-V2.5-Pro has no comparable published API token rate.

Cache-heavy agent loop

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

Grok 4.6
$0.2
Fits in one request
MiMo-V2.5-Pro
API rate not published
Fits in one request
Cached-input rate unavailable

MiMo-V2.5-Pro has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

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

Grok 4.6

$0.5 per 1M cached input tokens

xAI Grok 4.6 release notes

MiMo-V2.5-Pro

No comparable hosted API rate

Documented inputs

Grok 4.6

Not sourced

MiMo-V2.5-Pro

Not sourced

Documented outputs

Grok 4.6

Not sourced

MiMo-V2.5-Pro

Not sourced

Provider availability

Grok 4.6

Not sourced

MiMo-V2.5-Pro

Not sourced

Reasoning profile

Grok 4.6

Reasoning

MiMo-V2.5-Pro

Reasoning

Weight access

Grok 4.6

Proprietary

MiMo-V2.5-Pro

Proprietary

License

Grok 4.6

Proprietary

MiMo-V2.5-Pro

Proprietary

Release date

Grok 4.6

2026-08-12

MiMo-V2.5-Pro

2026-04-22

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 4.6 has the higher public score estimate, 69.19 versus 52.03, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
MiMo-V2.5-Pro has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Grok 4.6 or MiMo-V2.5-Pro?

Grok 4.6 has the higher public score estimate, 69.19 versus 52.03, 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 4.6 or MiMo-V2.5-Pro?

Grok 4.6 leads the public coding lane, 62 to 45.7, with Supported evidence for both models, although the 90% intervals overlap.

Which is better for agentic tasks, Grok 4.6 or MiMo-V2.5-Pro?

Grok 4.6 leads the public agentic tasks lane, 67.9 to 37.5, with Supported evidence for both models and non-overlapping 90% intervals.

Which costs less, Grok 4.6 or MiMo-V2.5-Pro?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Grok 4.6 or MiMo-V2.5-Pro?

MiMo-V2.5-Pro has the larger documented context window: 1M, compared with 500K.

Benchmark evidence

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

Browse raw public benchmark evidence25 rows

Agentic

  • Terminal-Bench 3.0

    Grok 4.626.5%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • APEX-Agents

    Grok 4.657.5%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Grok 4.678.3%
    Source
    MiMo-V2.5-Pro57.3%
    Source

    Grok 4.6 leads this result

  • ApprenticeBench

    Grok 4.613%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • Claw-Eval

    Grok 4.6—
    MiMo-V2.5-Pro63.8%
    Source

    Not directly comparable

  • τ³-bench results

    Grok 4.6—
    MiMo-V2.5-Pro72.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Grok 4.6—
    MiMo-V2.5-Pro68.4%
    Source

    Not directly comparable

  • Gert Labs

    Grok 4.6—
    MiMo-V2.5-Pro62.70%
    Source

    Not directly comparable

Coding

  • Bug Hunt Bench

    Grok 4.627 fixes
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • DeepSWE

    Grok 4.665.9%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • cursorBench32

    Grok 4.670.8%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • FrontierCode 1.1 Extended

    Grok 4.661.3%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • VulcanBench v3

    Grok 4.687.0%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • FrontierSWE v2

    Grok 4.625.3%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • LiveCodeBench (Vals)

    Grok 4.688.2%
    Source
    MiMo-V2.5-Pro81.4%
    Source

    Grok 4.6 leads this result

  • SWE-bench (Vals)

    Grok 4.695.6%
    Source
    MiMo-V2.5-Pro74.0%
    Source

    Grok 4.6 leads this result

  • SWE-bench Pro

    Grok 4.6—
    MiMo-V2.5-Pro57.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Grok 4.6—
    MiMo-V2.5-Pro68.4%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Grok 4.687.00%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • ARC-AGI-2

    Grok 4.667.1%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

  • ARC-AGI-3

    Grok 4.62.1%
    Source
    MiMo-V2.5-Pro—

    Not directly comparable

Knowledge

  • GPQA Diamond (Vals)

    Grok 4.694.7%
    Source
    MiMo-V2.5-Pro82.6%
    Source

    Grok 4.6 leads this result

  • MMLU-Pro (Vals)

    Grok 4.689.4%
    Source
    MiMo-V2.5-Pro84.6%
    Source

    Grok 4.6 leads this result

  • HLE

    Grok 4.6—
    MiMo-V2.5-Pro48%
    Source

    Not directly comparable

  • HLE w/o tools

    Grok 4.6—
    MiMo-V2.5-Pro34%
    Source

    Not directly comparable

25 public results · 5 shared

Watch Grok 4.6 vs MiMo-V2.5-Pro

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

Read a sample issue

Join 2,000+ readers.

Last updated September 25, 2026