Skip to main content

Model profile

MiMo-V2.5-Pro

XiaomiCurrentReleased Apr 22, 2026
Data verified
Overall Score
70.19Public #14 of 200Verified #12 of 99
Arena Elo
1466
Eligible category ranks
3of 8
Price (1M tokens)
Not listedAPI pricing
Speed
Not listed
Context
1M

Evidence coverage

31 of 323 tracked benchmarks are published. 9 are verified and 22 provisional. 6 of 8 categories are measured.

Updated July 22, 2026Methodology
Published / tracked
31 / 323
Verified
9
Provisional
22
Categories with evidence
6 / 8

Evidence by category

  • Agentic14 benchmarks
    Mixed evidence
  • Coding4 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge9 benchmarks
    Mixed evidence
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal1 benchmark
    Reported
  • Inst. Following1 benchmark
    Reported
ProprietaryReasoning
Confidence:
Low
pro

MiMo-V2.5-Pro ranks #14 out of 200 models on the public leaderboard with an overall score of 70.19/100. It also ranks #12 out of 99 on the verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.

MiMo-V2.5-Pro is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

MiMo-V2.5-Pro sits inside the MiMo-V2.5 family alongside MiMo-V2.5. BenchLM links it directly to MiMo-V2-Pro as the earlier related model in that lineage. This profile currently has 31 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Knowledge (#19), while its weakest is Agentic (#87). This performance profile makes it particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 67.7872.57

  1. GPT-5.6 Terra
    OpenAI
    #1172.57
    GPT-5.6 Terra is #11 with a score of 72.57.
    Compare
  2. Claude Opus 4.7
    Anthropic
    #1271.94
    Claude Opus 4.7 is #12 with a score of 71.94.
    Compare
  3. Muse Spark
    Meta
    #1371.04
    Muse Spark is #13 with a score of 71.04.
    Compare
  4. MiMo-V2.5-ProCurrent model
    Xiaomi
    #1470.19
    MiMo-V2.5-Pro is #14 with a score of 70.19.
  5. MiniMax M3
    MiniMax
    #1569.75
    MiniMax M3 is #15 with a score of 69.75.
    Compare
  6. Claude Opus 4.6
    Anthropic
    #1668.59
    Claude Opus 4.6 is #16 with a score of 68.59.
    Compare
  7. MiMo-V2-Pro
    Xiaomi
    #1767.78
    MiMo-V2-Pro is #17 with a score of 67.78.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Knowledge65%
    Eligible cohort rank #19 of 52Category score 74.8
  2. Coding74%
    Eligible cohort rank #32 of 122Category score 56.6
  3. Agentic27%
    Eligible cohort rank #87 of 119Category score 42.4

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #87 of 119Percentile 27thWeight 22%14 benchmarksMixed sources42.4
CodingRank #32 of 122Percentile 74thWeight 20%4 benchmarksMixed sources56.6
ReasoningWeight 17%2 benchmarksReportedScore pending
KnowledgeRank #19 of 52Percentile 65thWeight 12%9 benchmarksMixed sources74.8
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%1 benchmarkReportedScore pending
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1466±4.541,409
Coding1519±7.111,355
Math1475±13.52,036
Instruction Following1470±6.613,488
Creative Writing1433±8.36,880
Multi-turn1477±8.17,347
Hard Prompts1495±5.326,993
Hard Prompts (English)1506±6.712,804
Longer Query1487±6.317,664

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic14 benchmarks
Terminal-Bench 2.0Provider exact
68.4%Weighted 38%
Source: Xiaomi MiMo-V2.5-ProProvenance: Provider exact
Claw-EvalBenchmark exact
63.8%Display only
Source: Claw-Eval leaderboardProvenance: Claw-Eval reports this model as mimo_v25_pro in the official 2026-05-09 leaderboard snapshot. BenchLM stores the primary Pass^3 value on the local Claw-Eval display key.
GDPval-AAProvider exact
1265Display only
Source: Xiaomi MiMo-V2.5-ProProvenance: Provider exact
τ³-bench resultsProvider exact

τ³-Bench Tool-Agent-User Evaluation

72.9%Display only
Source: Xiaomi MiMo-V2.5-ProProvenance: Provider exact
AA Agentic IndexReported

Artificial Analysis Agentic Index

29.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

94.2%Display only
Source: Artificial Analysis: tau2-bench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

38.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
APEX-Agents-AAReported
2.4%Display only
Source: Artificial Analysis: apex-agents-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

62.70%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
AA BriefcaseReported

Artificial Analysis Briefcase

873Display only
Source: Artificial Analysis: aa-briefcase leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA ITBenchReported

Artificial Analysis ITBench-AA

38.2%Display only
Source: Artificial Analysis: itbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
terminalBenchHardReported
43.2%Display only
Source: Artificial Analysis: terminalbench-hard leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
aaTerminalBench21Reported
65.2%Display only
Source: Artificial Analysis: terminalbench-v2-1 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

73.3%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding4 benchmarks
SWE-bench ProProvider exact
57.2%Weighted 10%
Source: Xiaomi MiMo-V2.5-ProProvenance: Provider exact
Terminal-Bench 2.0Provider exact
68.4%Display only
Source: Xiaomi MiMo-V2.5-ProProvenance: Provider exact
AA Coding IndexReported

Artificial Analysis Coding Index

60.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

50.2%Display only
Source: Artificial Analysis: scicode leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

73.3%Display only
Source: Artificial Analysis: artificial-analysis-long-context-reasoning leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

4.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge9 benchmarks
HLEProvider exact

Humanity's Last Exam

48%Weighted 45%
Source: Xiaomi MiMo-V2.5-ProProvenance: Xiaomi reports Humanity's Last Exam at 48.0 with tools on the MiMo-V2.5-Pro launch chart.
HLE w/o toolsProvider exact

Humanity's Last Exam without tools

34%Display only
Source: Xiaomi MiMo-V2.5-ProProvenance: Xiaomi reports Humanity's Last Exam at 34.0 without tools on the MiMo-V2.5-Pro launch chart.
Artificial Analysis Intelligence IndexReported
42.2%Display only
Source: Artificial Analysis: artificial-analysis-intelligence-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

86.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

33.8%Display only
Source: Artificial Analysis: humanitys-last-exam leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

3.6%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

22.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

24.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA Openness IndexReported

Artificial Analysis Openness Index

38.9%Display only
Source: Artificial Analysis: artificial-analysis-openness-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Multimodal1 benchmark
Design Arena WebsiteReported

Design Arena Website Elo

1298Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

79.9%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.

MiMo-V2.5 Family

Pro

Canonical Entry

MiMo-V2.5

Related Earlier Model

MiMo-V2-Pro

Frequently Asked Questions

How does MiMo-V2.5-Pro perform overall in AI benchmarks?

MiMo-V2.5-Pro has 31 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is MiMo-V2.5-Pro good for knowledge and understanding?

MiMo-V2.5-Pro ranks #19 out of 52 models in knowledge and understanding benchmarks with an average score of 74.8. There are stronger options in this category.

Is MiMo-V2.5-Pro good for coding and programming?

MiMo-V2.5-Pro ranks #32 out of 122 models in coding and programming benchmarks with an average score of 56.6. There are stronger options in this category.

Is MiMo-V2.5-Pro good for reasoning and logic?

MiMo-V2.5-Pro has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is MiMo-V2.5-Pro good for agentic tool use and computer tasks?

MiMo-V2.5-Pro ranks #87 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 42.4. There are stronger options in this category.

Is MiMo-V2.5-Pro good for multimodal and grounded tasks?

MiMo-V2.5-Pro has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is MiMo-V2.5-Pro good for instruction following?

MiMo-V2.5-Pro has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to MiMo-V2.5-Pro?

MiMo-V2.5-Pro belongs to the MiMo-V2.5 family. Related variants on BenchLM include MiMo-V2.5.

Does MiMo-V2.5-Pro have full benchmark coverage on BenchLM?

Not yet. MiMo-V2.5-Pro currently has 31 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of MiMo-V2.5-Pro?

MiMo-V2.5-Pro has a published context window of 1M, which determines how much text it can process in a single interaction.

Last updated: July 22, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.