wehub-resource-sync
52 lines
1.1 KiB
TOML
52 lines
1.1 KiB
TOML
name = "Kimi K2.5"
|
|
description = "Earlier Kimi frontier model for long-context agents, coding, and multimodal work"
|
|
family = "kimi-k2"
|
|
release_date = "2026-01"
|
|
last_updated = "2026-01"
|
|
attachment = false
|
|
reasoning = true
|
|
temperature = false
|
|
tool_call = true
|
|
structured_output = true
|
|
knowledge = "2025-01"
|
|
open_weights = true
|
|
|
|
[limit]
|
|
context = 262_144
|
|
output = 262_144
|
|
|
|
[modalities]
|
|
input = ["text", "image", "video"]
|
|
output = ["text"]
|
|
|
|
[[weights]]
|
|
label = "Hugging Face"
|
|
url = "https://huggingface.co/moonshotai/Kimi-K2.5"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Bench Verified"
|
|
score = 70.8
|
|
metric = "resolved"
|
|
source = "https://www.swebench.com/"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Atlas Codebase QnA"
|
|
score = 13.1
|
|
metric = "score"
|
|
harness = "Mini-SWE-Agent"
|
|
source = "https://labs.scale.com/leaderboard/sweatlas-qna"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Atlas Refactoring"
|
|
score = 20.95
|
|
metric = "score"
|
|
harness = "Mini-SWE-Agent"
|
|
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Atlas Test Writing"
|
|
score = 25.77
|
|
metric = "score"
|
|
harness = "Mini-SWE-Agent"
|
|
source = "https://labs.scale.com/leaderboard/sweatlas-tw"
|