Skip to main content

Model comparison

Kimi K2.5 vs MiMo-V2-Flash

Data verified

Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Moonshot AI
59.66/100
Margin
5.6pts
← winning
54.06/100
0 category wins2 category wins

Public leaderboard positions: Kimi K2.5 #54 (Supported); MiMo-V2-Flash #91 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K2.5 and MiMo-V2-Flash share 19 comparable benchmark results. 2 of 8 categories are comparable. 44 results are unique to Kimi K2.5; 0 to MiMo-V2-Flash.

Updated July 20, 2026
Shared results
19
Kimi K2.5 only
44
MiMo-V2-Flash only
0
Comparable categories
2 / 8

Pick Kimi K2.5 if you want the stronger benchmark profile. MiMo-V2-Flash only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Kimi K2.5 is clearly ahead on the BenchAlign aggregate, 59.66 to 54.06. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K2.5 is also the more expensive model on tokens at $0.60 input / $3.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for MiMo-V2-Flash. That is roughly Infinityx on output cost alone. MiMo-V2-Flash is the reasoning model in the pair, while Kimi K2.5 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 Kimi K2.5 and MiMo-V2-Flash
CategoryKimi K2.5ΔMiMo-V2-Flash
KnowledgeKimi K2.556.9Margin 27.8MiMo-V2-Flash84.7
CodingKimi K2.559.4Margin 14.0MiMo-V2-Flash73.4
AgenticKimi K2.555.0MarginNo overlapMiMo-V2-FlashNot measured
ReasoningKimi K2.561.0MarginNo overlapMiMo-V2-FlashNot measured
MathKimi K2.560.6MarginNo overlapMiMo-V2-FlashNot measured
MultilingualKimi K2.582.3MarginNo overlapMiMo-V2-FlashNot measured
MultimodalKimi K2.578.5MarginNo overlapMiMo-V2-FlashNot measured
Inst. FollowingKimi K2.593.9MarginNo overlapMiMo-V2-FlashNot measured

Decisive benchmark drivers

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

More
A · Kimi K2.5B · MiMo-V2-Flash
  1. GPQA

    Knowledge
    Source ↗
    A 87.6%B 83.7%
    Winner: Kimi K2.5Δ 3.9
    GPQA: Kimi K2.5 scored 87.6%; MiMo-V2-Flash scored 83.7%. Kimi K2.5 wins this benchmark.
  2. SWE-bench Verified

    Coding
    Source ↗
    A 76.8%B 73.4%
    Winner: Kimi K2.5Δ 3.4
    SWE-bench Verified: Kimi K2.5 scored 76.8%; MiMo-V2-Flash scored 73.4%. Kimi K2.5 wins this benchmark.
  3. MMLU-Pro

    Knowledge
    Source ↗
    A 87.1%B 84.9%
    Winner: Kimi K2.5Δ 2.2
    MMLU-Pro: Kimi K2.5 scored 87.1%; MiMo-V2-Flash scored 84.9%. Kimi K2.5 wins this benchmark.

Operational comparison

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

MetricKimi K2.5MiMo-V2-FlashComparison
Input / output priceUSD per 1M tokensKimi K2.5$0.6 input / $3 outputMiMo-V2-Flash$0 input / $0 outputMiMo-V2-Flash has the lower combined listed price.
Generation speedtokens per secondKimi K2.545 tok/sMiMo-V2-Flash129 tok/sMiMo-V2-Flash has the higher measured throughput.
First-answer latencyseconds to first tokenKimi K2.52.38 sMiMo-V2-Flash2.14 sMiMo-V2-Flash reaches the first token sooner.
Context windowmaximum listed tokensKimi K2.5256KMiMo-V2-Flash256KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkKimi K2.5MiMo-V2-FlashResult
Terminal-Bench 2.0Source 50.8%Not comparable
BrowseCompSource 60.6%Not comparable
Claw-EvalSource 52.3%Not comparable
QwenClawBenchSource 54.3%Not comparable
τ³-bench resultsSource 65.7%Not comparable
DeepSearchQASource 77.1%Not comparable
DeepPlanningSource 14.4%Not comparable
ToolathlonSource 27.8%Not comparable
MCP AtlasSource 29.5%Not comparable
MCP-TasksSource 59.1%Not comparable
WideResearchSource 72.7%Not comparable
τ²-bench resultsSource 95.9%83.9%Kimi K2.5 leads
APEX-Agents-AASource 11.5%Not comparable
Gert LabsSource 45.88%Not comparable
ResearchClawBenchSource 14.0%Not comparable
JobBenchSource 8.7%Not comparable
AA Agentic IndexSource 21.7%12.0%Kimi K2.5 leads
GDPval-AASource 25.4%16.7%Kimi K2.5 leads
GDPval-AASource 1009833Kimi K2.5 leads
CodingMiMo-V2-Flash wins
BenchmarkKimi K2.5MiMo-V2-FlashResult
SWE-bench VerifiedSource 76.8%73.4%Kimi K2.5 leads
SWE-bench Verified*Source 70.8%Not comparable
LiveCodeBench v6Source 85.0%Not comparable
SWE-bench ProSource 50.7%Not comparable
SWE MultilingualSource 73%Not comparable
SWE-RebenchSource 58.5%Not comparable
React Native EvalsSource 77.2%Not comparable
SciCodeSource 48.7%Not comparable
AA-SciCodeSource 49.0%25.9%Kimi K2.5 leads
AA Coding IndexSource 46.8%49.8%MiMo-V2-Flash leads
Reasoning
BenchmarkKimi K2.5MiMo-V2-FlashResult
LongBench v2Source 61%Not comparable
AA-LCRSource 65.3%31.3%Kimi K2.5 leads
CritPtSource 3.1%0.0%Kimi K2.5 leads
KnowledgeMiMo-V2-Flash wins
BenchmarkKimi K2.5MiMo-V2-FlashResult
GPQASource 87.6%83.7%Kimi K2.5 leads
GPQA-DSource 87.6%Not comparable
SuperGPQASource 69.2%Not comparable
MMLU-ProSource 87.1%84.9%Kimi K2.5 leads
MMLU-Pro (Arcee)Source 87.1%Not comparable
HLESource 30.1%Not comparable
Artificial Analysis Intelligence IndexSource 35.4%24.7%Kimi K2.5 leads
AA-GPQA DiamondSource 87.9%65.6%Kimi K2.5 leads
AA-HLESource 29.4%8.0%Kimi K2.5 leads
AA-Omniscience IndexSource -8.1%-48.5%Kimi K2.5 leads
AA-Omniscience AccuracySource 34.3%15.2%Kimi K2.5 leads
AA-Omniscience Hallucination RateSource 64.6%75.1%Kimi K2.5 leads
Math
BenchmarkKimi K2.5MiMo-V2-FlashResult
AIME 2025Source 96.1%94.1%Kimi K2.5 leads
AIME26Source 95.8%Not comparable
AIME25 (Arcee)Source 96.3%Not comparable
HMMT Feb 2025Source 95.4%Not comparable
HMMT Nov 2025Source 91.1%Not comparable
HMMT Feb 2026Source 87.1%Not comparable
MMAnswerBenchSource 81.8%Not comparable
FrontierMath v2 (Tiers 1-3)Source 27.900%Not comparable
FrontierMath v2 (Tier 4)Source 4.200%Not comparable
Multilingual
BenchmarkKimi K2.5MiMo-V2-FlashResult
MMLU-ProXSource 82.3%Not comparable
NOVA-63Source 56.0%Not comparable
Multimodal
BenchmarkKimi K2.5MiMo-V2-FlashResult
MMMU-ProSource 78.5%Not comparable
Video-MMESource 87.4%Not comparable
MMVUSource 80.4%Not comparable
VideoMMMUSource 86.6%Not comparable
AA-MMMU-ProSource 75.4%Not comparable
Design Arena WebsiteSource 1282Not comparable
Inst. Following
BenchmarkKimi K2.5MiMo-V2-FlashResult
IFEvalSource 93.9%Not comparable
AA-IFBenchSource 70.2%39.9%Kimi K2.5 leads
Frequently Asked Questions (3)

Which is better, Kimi K2.5 or MiMo-V2-Flash?

Kimi K2.5 is ahead on BenchLM's BenchAlign leaderboard, 59.66 to 54.06. The biggest single separator in this matchup is GPQA, where the scores are 87.6% and 83.7%.

Which is better for knowledge tasks, Kimi K2.5 or MiMo-V2-Flash?

MiMo-V2-Flash has the edge for knowledge tasks in this comparison, averaging 84.7 versus 56.9. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, Kimi K2.5 or MiMo-V2-Flash?

MiMo-V2-Flash has the edge for coding in this comparison, averaging 73.4 versus 59.4. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
MiMo-V2-Flash
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

Related Comparisons

Last updated: July 20, 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.