Coding
Directional only- Kimi K2.5
- 59.4
- MiMo-V2-Pro
- 78.0
- Weighted basis
- 4 vs 1 rows
- Reading
- Directional only
Model comparison
Kimi K2.5 vs MiMo-V2-Pro
Updated August 1, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
20 confirmed releases in the last 30 daysSee provider release alerts
MiMo-V2-Pro has the higher public score estimate, 66.75 versus 58.75, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
4 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.
Long documents
Prompts that approach the documented context limit
MiMo-V2-Pro
MiMo-V2-Pro has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
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: rate-fallback
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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
41 Kimi K2.5 only
4 Shared
- Shared results
- 4
- Kimi K2.5 only
- 41
- MiMo-V2-Pro only
- 0
- Like-for-like categories
- 0 / 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.
Agentic
Not comparable- Kimi K2.5
- 55.0
- MiMo-V2-Pro
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Kimi K2.5
- 61.0
- MiMo-V2-Pro
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Kimi K2.5
- 56.9
- MiMo-V2-Pro
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Kimi K2.5
- 60.6
- MiMo-V2-Pro
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Kimi K2.5
- 82.3
- MiMo-V2-Pro
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Kimi K2.5
- 78.5
- MiMo-V2-Pro
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Kimi K2.5
- 93.9
- MiMo-V2-Pro
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
| Category | Kimi K2.5 | MiMo-V2-Pro | Weighted basis | Reading |
|---|---|---|---|---|
| Coding | 59.4 | 78.0 | Directional only4 vs 1 rows | Directional only |
| Agentic | 55.0 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Reasoning | 61.0 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Knowledge | 56.9 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Math | 60.6 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Multilingual | 82.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Multimodal | 78.5 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | 93.9 | Not measured | Not comparable1 vs 0 rows | 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.
SWE-bench Verified
Coding
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
- Kimi K2.5
- $0.0021
- Fits in one request
- MiMo-V2-Pro
- API rate not published
- Fits in one request
MiMo-V2-Pro has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Kimi K2.5
- $0.039
- Fits in one request
- MiMo-V2-Pro
- API rate not published
- Fits in one request
MiMo-V2-Pro has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Kimi K2.5
- $0.162
- Fits in one request
- Cached input priced at the published list-input rate
- MiMo-V2-Pro
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Kimi K2.5 has no published cached-input rate, so cached tokens use its listed input rate. MiMo-V2-Pro has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationKimi K2.5MiMo-V2-Pro
Context window
Maximum documented context; output-token limits may be lower.
Kimi K2.5
256K
MiMo-V2-Pro
1M
API model ID
Kimi K2.5
Not sourced
MiMo-V2-Pro
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K2.5
Not published
MiMo-V2-Pro
No comparable hosted API rate
Documented inputs
Kimi K2.5
Not sourced
MiMo-V2-Pro
Not sourced
Documented outputs
Kimi K2.5
Not sourced
MiMo-V2-Pro
Not sourced
Provider availability
Kimi K2.5
Not sourced
MiMo-V2-Pro
Not sourced
Reasoning profile
Kimi K2.5
Non-Reasoning
MiMo-V2-Pro
Reasoning
Weight access
Kimi K2.5
Open Weight
MiMo-V2-Pro
Proprietary
License
Kimi K2.5
Open Weight
MiMo-V2-Pro
Proprietary
Release date
Kimi K2.5
2026-02-01
MiMo-V2-Pro
2026-03-18
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
- MiMo-V2-Pro has the higher public score estimate, 66.75 versus 58.75, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- MiMo-V2-Pro has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
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-Pro
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence45 rows
Agentic
Terminal-Bench 2.0
Kimi K2.550.8%SourceMiMo-V2-Pro—Not directly comparable
BrowseComp
Kimi K2.560.6%SourceMiMo-V2-Pro—Not directly comparable
Claw-Eval
Shared sourceKimi K2.552.3%MiMo-V2-Pro57.8%MiMo-V2-Pro leads this result
QwenClawBench
Kimi K2.554.3%SourceMiMo-V2-Pro—Not directly comparable
τ³-bench results
Kimi K2.565.7%SourceMiMo-V2-Pro—Not directly comparable
DeepSearchQA
Kimi K2.577.1%SourceMiMo-V2-Pro—Not directly comparable
DeepPlanning
Kimi K2.514.4%SourceMiMo-V2-Pro—Not directly comparable
Toolathlon
Kimi K2.527.8%SourceMiMo-V2-Pro—Not directly comparable
MCP Atlas
Kimi K2.529.5%SourceMiMo-V2-Pro—Not directly comparable
MCP-Tasks
Kimi K2.559.1%SourceMiMo-V2-Pro—Not directly comparable
WideResearch
Kimi K2.572.7%SourceMiMo-V2-Pro—Not directly comparable
Gert Labs
Shared sourceKimi K2.545.88%MiMo-V2-Pro36.68%Kimi K2.5 leads this result
ResearchClawBench
Shared sourceKimi K2.514.0%MiMo-V2-Pro15.3%MiMo-V2-Pro leads this result
JobBench
Kimi K2.58.7%SourceMiMo-V2-Pro—Not directly comparable
Coding
SWE-bench Verified
Kimi K2.576.8%SourceMiMo-V2-Pro78%SourceMiMo-V2-Pro leads this result
SWE-bench Verified*
Kimi K2.570.8%SourceMiMo-V2-Pro—Not directly comparable
LiveCodeBench v6
Kimi K2.585.0%SourceMiMo-V2-Pro—Not directly comparable
SWE-bench Pro
Kimi K2.550.7%SourceMiMo-V2-Pro—Not directly comparable
SWE Multilingual
Kimi K2.573%SourceMiMo-V2-Pro—Not directly comparable
SWE-Rebench
Kimi K2.558.5%SourceMiMo-V2-Pro—Not directly comparable
React Native Evals
Kimi K2.577.2%SourceMiMo-V2-Pro—Not directly comparable
SciCode
Kimi K2.548.7%SourceMiMo-V2-Pro—Not directly comparable
Reasoning
LongBench v2
Kimi K2.561%SourceMiMo-V2-Pro—Not directly comparable
Knowledge
GPQA
Kimi K2.587.6%SourceMiMo-V2-Pro—Not directly comparable
GPQA-D
Kimi K2.587.6%SourceMiMo-V2-Pro—Not directly comparable
SuperGPQA
Kimi K2.569.2%SourceMiMo-V2-Pro—Not directly comparable
MMLU-Pro
Kimi K2.587.1%SourceMiMo-V2-Pro—Not directly comparable
MMLU-Pro (Arcee)
Kimi K2.587.1%SourceMiMo-V2-Pro—Not directly comparable
HLE
Kimi K2.530.1%SourceMiMo-V2-Pro—Not directly comparable
Math
AIME 2025
Kimi K2.596.1%SourceMiMo-V2-Pro—Not directly comparable
AIME26
Kimi K2.595.8%SourceMiMo-V2-Pro—Not directly comparable
AIME25 (Arcee)
Kimi K2.596.3%SourceMiMo-V2-Pro—Not directly comparable
HMMT Feb 2025
Kimi K2.595.4%SourceMiMo-V2-Pro—Not directly comparable
HMMT Nov 2025
Kimi K2.591.1%SourceMiMo-V2-Pro—Not directly comparable
HMMT Feb 2026
Kimi K2.587.1%SourceMiMo-V2-Pro—Not directly comparable
MMAnswerBench
Kimi K2.581.8%SourceMiMo-V2-Pro—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Kimi K2.527.900%SourceMiMo-V2-Pro—Not directly comparable
FrontierMath v2 (Tier 4)
Kimi K2.54.200%SourceMiMo-V2-Pro—Not directly comparable
Multilingual
Multimodal
Instruction following
IFEval
Kimi K2.593.9%SourceMiMo-V2-Pro—Not directly comparable
Frequently asked questions
Which is better, Kimi K2.5 or MiMo-V2-Pro?
MiMo-V2-Pro has the higher public score estimate, 66.75 versus 58.75, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Kimi K2.5 or MiMo-V2-Pro?
The current coding 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 is better for agentic tasks, Kimi K2.5 or MiMo-V2-Pro?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Kimi K2.5 or MiMo-V2-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, Kimi K2.5 or MiMo-V2-Pro?
MiMo-V2-Pro has the larger documented context window: 1M, compared with 256K.
Related comparisons
Last updated August 1, 2026
Watch Kimi K2.5 vs MiMo-V2-Pro
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.