Skip to main content

Model comparison

Grok 4.20 vs MiMo-V2.5

Data verified

Head-to-head evidence from 6 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

54.68/100
Margin
3.9pts
winning →
Xiaomi
58.62/100
1 category wins2 category wins

Public leaderboard positions: Grok 4.20 #88 (Estimated); MiMo-V2.5 #62 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Grok 4.20 and MiMo-V2.5 share 6 comparable benchmark results. 3 of 8 categories are comparable. 12 results are unique to Grok 4.20; 5 to MiMo-V2.5.

Updated July 21, 2026
Shared results
6
Grok 4.20 only
12
MiMo-V2.5 only
5
Comparable categories
3 / 8

Pick MiMo-V2.5 if you want the stronger benchmark profile. Grok 4.20 only becomes the better choice if coding is the priority or you need the larger 2M context window.

Confidence note. This is a partial-evidence comparison with 6 shared benchmark results across 3 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

MiMo-V2.5 is clearly ahead on the BenchAlign aggregate, 58.62 to 54.68. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

MiMo-V2.5's sharpest advantage is in agentic, where it averages 65.8 against 47.1. The single biggest benchmark swing on the page is CharXiv, 60.9% to 81%. Grok 4.20 does hit back in coding, so the answer changes if that is the part of the workload you care about most.

Grok 4.20 gives you the larger context window at 2M, compared with 1M for MiMo-V2.5.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Grok 4.20 and MiMo-V2.5
CategoryGrok 4.20ΔMiMo-V2.5
AgenticGrok 4.2047.1Margin 18.7MiMo-V2.565.8
CodingGrok 4.2067.1Margin 11.0MiMo-V2.556.1
MultimodalGrok 4.2070.1Margin 8.9MiMo-V2.579.0
ReasoningGrok 4.2053.3MarginNo overlapMiMo-V2.5Not measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Grok 4.20B · MiMo-V2.5
  1. CharXiv

    Multimodal
    Source ↗
    A 60.9%B 81%
    Winner: MiMo-V2.5Δ 20.1
    CharXiv: Grok 4.20 scored 60.9%; MiMo-V2.5 scored 81%. MiMo-V2.5 wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 47.1%B 65.8%
    Winner: MiMo-V2.5Δ 18.7
    Terminal-Bench 2.0: Grok 4.20 scored 47.1%; MiMo-V2.5 scored 65.8%. MiMo-V2.5 wins this benchmark.
  3. SWE-bench Pro

    Coding
    Source ↗
    A 51.8%B 56.1%
    Winner: MiMo-V2.5Δ 4.3
    SWE-bench Pro: Grok 4.20 scored 51.8%; MiMo-V2.5 scored 56.1%. MiMo-V2.5 wins this benchmark.
  4. MMMU-Pro

    Multimodal
    Source ↗
    A 75.2%B 77.9%
    Winner: MiMo-V2.5Δ 2.7
    MMMU-Pro: Grok 4.20 scored 75.2%; MiMo-V2.5 scored 77.9%. MiMo-V2.5 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGrok 4.20MiMo-V2.5Comparison
Input / output priceUSD per 1M tokensGrok 4.20$2 input / $6 outputMiMo-V2.5Not availableA complete price comparison is not available.
Generation speedtokens per secondGrok 4.20233 tok/sMiMo-V2.5Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGrok 4.2010.33 sMiMo-V2.5Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensGrok 4.202MMiMo-V2.51MGrok 4.20 lists the larger context window.

Benchmark Deep Dive

AgenticMiMo-V2.5 wins
BenchmarkGrok 4.20MiMo-V2.5Result
Terminal-Bench 2.0Source 47.1%65.8%MiMo-V2.5 leads
DeepSearchQASource 62.8%Not comparable
Gert LabsSource 38.36%46.89%MiMo-V2.5 leads
Claw-EvalSource 62.3%Not comparable
MM-ClawBenchSource 23.8%Not comparable
ResearchClawBenchSource 16.9%Not comparable
CodingGrok 4.20 wins
BenchmarkGrok 4.20MiMo-V2.5Result
LiveCodeBench ProSource 74.2%Not comparable
SWE-bench VerifiedSource 76.7%Not comparable
SWE-bench ProSource 51.8%56.1%MiMo-V2.5 leads
Vibe Code BenchSource 4.06%Not comparable
Terminal-Bench 2.0Source 65.8%Not comparable
Reasoning
BenchmarkGrok 4.20MiMo-V2.5Result
ARC-AGI-2Source 53.3%Not comparable
Knowledge
BenchmarkGrok 4.20MiMo-V2.5Result
GPQA-DSource 88.5%Not comparable
HLE w/o toolsSource 31.6%Not comparable
HealthBench HardSource 20.3%Not comparable
MedXpertQA (Text)Source 50.2%Not comparable
MultimodalMiMo-V2.5 wins
BenchmarkGrok 4.20MiMo-V2.5Result
MMMU-ProSource 75.2%77.9%MiMo-V2.5 leads
CharXivSource 60.9%81%MiMo-V2.5 leads
ERQASource 54.1%Not comparable
SimpleVQASource 57.4%Not comparable
MedXpertQA (MM)Source 65.8%Not comparable
Design Arena WebsiteSource 12571291MiMo-V2.5 leads
Video-MME (with subtitle)Source 87.7%Not comparable
Frequently Asked Questions (4)

Which is better, Grok 4.20 or MiMo-V2.5?

MiMo-V2.5 is ahead on BenchLM's BenchAlign leaderboard, 58.62 to 54.68. The biggest single separator in this matchup is CharXiv, where the scores are 60.9% and 81%.

Which is better for coding, Grok 4.20 or MiMo-V2.5?

Grok 4.20 has the edge for coding in this comparison, averaging 67.1 versus 56.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Grok 4.20 or MiMo-V2.5?

MiMo-V2.5 has the edge for agentic tasks in this comparison, averaging 65.8 versus 47.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Grok 4.20 or MiMo-V2.5?

MiMo-V2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 79 versus 70.1. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 21, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.