name = "MiniMax-M2.5"
description = "Prior MiniMax coding model for agent workflows, office edits, and automation"
family = "minimax"
release_date = "2026-02-12"
last_updated = "2026-02-12"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true

[limit]
context = 204_800
output = 131_072

[modalities]
input = ["text"]
output = ["text"]

[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/MiniMaxAI/MiniMax-M2.5"

[[benchmarks]]
name = "SWE-Bench Verified"
score = 75.8
metric = "resolved"
source = "https://www.swebench.com/"

[[benchmarks]]
name = "SWE-Atlas Codebase QnA"
score = 10.3
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-qna"

[[benchmarks]]
name = "SWE-Atlas Refactoring"
score = 19.52
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"

[[benchmarks]]
name = "SWE-Atlas Test Writing"
score = 18.6
metric = "score"
harness = "Mini-SWE-Agent"
source = "https://labs.scale.com/leaderboard/sweatlas-tw"