Skip to main content

Model profile

MiniMax M2.5

MiniMaxSupersededReleased Oct 1, 2025
Data verified
Superseded:MiniMax has released newer models in this line —MiniMax M2.7
Overall Score
59.52Public #55 of 200Verified #42 of 99
Arena Elo
1391
Eligible category ranks
1of 8
Price (1M tokens)
$0.3 in / $1.2 out
API pricing
Speed
46tok/s
Context
128K

Evidence coverage

1 of 321 tracked benchmarks is published. 1 is verified and 0 provisional. 1 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
1 / 321
Verified
1
Provisional
0
Categories with evidence
1 / 8

Evidence by category

  • Agentic0 benchmarks
    Not measured
  • Coding1 benchmark
    Verified
  • Reasoning0 benchmarks
    Not measured
  • Knowledge0 benchmarks
    Not measured
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following0 benchmarks
    Not measured
ProprietaryNon-Reasoning
Confidence:
Low
base

MiniMax M2.5 ranks #55 out of 200 models on the public leaderboard with an overall score of 59.52/100. It also ranks #42 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

MiniMax M2.5 is a proprietary model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 1 of 321 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 Coding (#43). This performance profile makes it particularly well-suited for software development and code generation tasks.

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 59.159.77

  1. GLM-5 (Reasoning)
    Z.AI
    #5259.77
    GLM-5 (Reasoning) is #52 with a score of 59.77.
    Compare
  2. Qwen 3.6 Max (preview)
    Alibaba
    #5359.72
    Qwen 3.6 Max (preview) is #53 with a score of 59.72.
    Compare
  3. Kimi K2.5
    Moonshot AI
    #5459.66
    Kimi K2.5 is #54 with a score of 59.66.
    Compare
  4. MiniMax M2.5Current model
    MiniMax
    #5559.52
    MiniMax M2.5 is #55 with a score of 59.52.
  5. Qwen3.5 397B (Reasoning)
    Alibaba
    #5659.5
    Qwen3.5 397B (Reasoning) is #56 with a score of 59.5.
    Compare
  6. Kimi K2.5 (Reasoning)
    Moonshot AI
    #5759.35
    Kimi K2.5 (Reasoning) is #57 with a score of 59.35.
    Compare
  7. GPT-5.2-Codex
    OpenAI
    #5859.1
    GPT-5.2-Codex is #58 with a score of 59.1.
    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. Coding65%
    Eligible cohort rank #43 of 122Category score 53.6

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
AgenticWeight 22%0 benchmarksNot measuredNot measured
CodingRank #43 of 122Percentile 65thWeight 20%1 benchmarkVerified53.6
ReasoningWeight 17%0 benchmarksNot measuredNot measured
KnowledgeWeight 12%0 benchmarksNot measuredNot measured
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingWeight 5%0 benchmarksNot measuredNot measured

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 Overall1391±4.041,138
Coding1444±6.610,887
Math1397±12.12,429
Instruction Following1381±6.112,993
Creative Writing1358±8.16,403
Multi-turn1394±7.77,346
Hard Prompts1416±5.025,558
Hard Prompts (English)1431±6.312,416
Longer Query1403±6.015,182

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.

Coding1 benchmark
Vibe Code BenchBenchmark exact

Vibe Code Bench v1.1

14.85%Display only
Source: Vals AI: Vibe Code Bench v1.1Provenance: Vals Vibe Code Bench v1.1 reports this exact row under minimax/MiniMax-M2.5; BenchLM stores it on the local vibeCodeBench key.

Frequently Asked Questions

How does MiniMax M2.5 perform overall in AI benchmarks?

MiniMax M2.5 has 1 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is MiniMax M2.5 good for coding and programming?

MiniMax M2.5 ranks #43 out of 122 models in coding and programming benchmarks with an average score of 53.6. There are stronger options in this category.

Does MiniMax M2.5 have full benchmark coverage on BenchLM?

Not yet. MiniMax M2.5 currently has 1 published benchmark scores out of the 321 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 MiniMax M2.5?

MiniMax M2.5 has a published context window of 128K, which determines how much text it can process in a single interaction.

Last updated: July 20, 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.