Skip to main content

Model comparison

Inkling vs MiMo-V2.5

Data verified

Head-to-head evidence from 5 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Thinking Machines Lab
69/100
Margin
10.6pts
← winning
Xiaomi
58.41/100
2 category wins1 category wins

Verified leaderboard positions: Inkling #17; MiMo-V2.5 unranked

BenchAlign evidence: Inkling not scored; MiMo-V2.5 estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Inkling and MiMo-V2.5 share 5 comparable benchmark results. 3 of 8 categories are comparable. 11 results are unique to Inkling; 6 to MiMo-V2.5.

Updated July 15, 2026
Shared results
5
Inkling only
11
MiMo-V2.5 only
6
Comparable categories
3 / 8

Pick Inkling if you want the stronger benchmark profile. MiMo-V2.5 only becomes the better choice if multimodal & grounded is the priority or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 5 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

Inkling is clearly ahead on the provisional aggregate, 69 to 64. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Inkling's sharpest advantage is in coding, where it averages 68.6 against 56.1. The single biggest benchmark swing on the page is MMMU-Pro, 73.5% to 77.9%. MiMo-V2.5 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.

MiMo-V2.5 is the reasoning model in the pair, while Inkling is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

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 Inkling and MiMo-V2.5
CategoryInklingΔMiMo-V2.5
CodingInkling68.6Margin 12.5MiMo-V2.556.1
AgenticInkling69.4Margin 3.6MiMo-V2.565.8
MultimodalInkling76.5Margin 2.5MiMo-V2.579.0
KnowledgeInkling51.7MarginNo overlapMiMo-V2.5Not measured
MathInkling97.1MarginNo overlapMiMo-V2.5Not measured
Inst. FollowingInkling79.8MarginNo overlapMiMo-V2.5Not measured

Decisive benchmark drivers

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

More
A · InklingB · MiMo-V2.5
  1. MMMU-Pro

    Multimodal
    Source ↗
    A 73.5%B 77.9%
    Winner: MiMo-V2.5Δ 4.4
    MMMU-Pro: Inkling scored 73.5%; MiMo-V2.5 scored 77.9%. MiMo-V2.5 wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 63.8%B 65.8%
    Winner: MiMo-V2.5Δ 2
    Terminal-Bench 2.0: Inkling scored 63.8%; MiMo-V2.5 scored 65.8%. MiMo-V2.5 wins this benchmark.
  3. SWE-bench Pro

    Coding
    Source ↗
    A 54.3%B 56.1%
    Winner: MiMo-V2.5Δ 1.8
    SWE-bench Pro: Inkling scored 54.3%; MiMo-V2.5 scored 56.1%. MiMo-V2.5 wins this benchmark.
  4. CharXiv

    Multimodal
    Source ↗
    A 82%B 81%
    Winner: InklingΔ 1
    CharXiv: Inkling scored 82%; MiMo-V2.5 scored 81%. Inkling wins this benchmark.

Operational comparison

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

MetricInklingMiMo-V2.5Comparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputMiMo-V2.5Not availableA complete price comparison is not available.
Generation speedtokens per secondInklingNot availableMiMo-V2.5Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableMiMo-V2.5Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MMiMo-V2.51MListed context windows are equal.

Benchmark Deep Dive

AgenticInkling wins
BenchmarkInklingMiMo-V2.5Result
Terminal-Bench 2.0Source 63.8%65.8%MiMo-V2.5 leads
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
Claw-EvalSource 62.3%Not comparable
MM-ClawBenchSource 23.8%Not comparable
Gert LabsSource 46.89%Not comparable
ResearchClawBenchSource 16.9%Not comparable
CodingInkling wins
BenchmarkInklingMiMo-V2.5Result
SWE-bench VerifiedSource 77.6%Not comparable
SWE-bench ProSource 54.3%56.1%MiMo-V2.5 leads
Terminal-Bench 2.0Source 63.8%65.8%MiMo-V2.5 leads
Knowledge
BenchmarkInklingMiMo-V2.5Result
GPQASource 87.9%Not comparable
GPQA-DSource 87.9%Not comparable
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
Math
BenchmarkInklingMiMo-V2.5Result
AIME26Source 97.1%Not comparable
MultimodalMiMo-V2.5 wins
BenchmarkInklingMiMo-V2.5Result
MMMU-ProSource 73.5%77.9%MiMo-V2.5 leads
CharXivSource 82%81%Inkling leads
CharXiv w/o toolsSource 78.1%Not comparable
Video-MME (with subtitle)Source 87.7%Not comparable
Design Arena WebsiteSource 1295Not comparable
Inst. Following
BenchmarkInklingMiMo-V2.5Result
IFBenchSource 79.8%Not comparable
Frequently Asked Questions (4)

Which is better, Inkling or MiMo-V2.5?

Inkling is ahead on BenchLM's provisional leaderboard, 69 to 64. The biggest single separator in this matchup is MMMU-Pro, where the scores are 73.5% and 77.9%.

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

Inkling has the edge for coding in this comparison, averaging 68.6 versus 56.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

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

Inkling has the edge for agentic tasks in this comparison, averaging 69.4 versus 65.8. 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, Inkling or MiMo-V2.5?

MiMo-V2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 79 versus 76.5. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 15, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.