wehub-resource-sync
73 lines
1.6 KiB
TOML
73 lines
1.6 KiB
TOML
name = "Claude Sonnet 5"
|
|
description = "Everyday Claude agent model for coding, planning, browsing, and general work"
|
|
family = "claude-sonnet"
|
|
release_date = "2026-06-30"
|
|
last_updated = "2026-06-30"
|
|
attachment = true
|
|
reasoning = true
|
|
temperature = false
|
|
tool_call = true
|
|
knowledge = "2026-01-31"
|
|
open_weights = false
|
|
|
|
[limit]
|
|
context = 1_000_000
|
|
output = 128_000
|
|
|
|
[modalities]
|
|
input = ["text", "image", "pdf"]
|
|
output = ["text"]
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Bench Verified"
|
|
score = 85.2
|
|
metric = "resolved"
|
|
source = "https://www.anthropic.com/news/claude-sonnet-5"
|
|
date = "2026-06-30"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Bench Pro"
|
|
score = 63.2
|
|
metric = "resolve rate"
|
|
source = "https://www.anthropic.com/news/claude-sonnet-5"
|
|
date = "2026-06-30"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Bench Multilingual"
|
|
score = 78.3
|
|
metric = "resolve rate"
|
|
source = "https://www.anthropic.com/news/claude-sonnet-5"
|
|
date = "2026-06-30"
|
|
|
|
[[benchmarks]]
|
|
name = "Terminal-Bench"
|
|
score = 80.4
|
|
metric = "success rate"
|
|
harness = "Terminus-2"
|
|
version = "2.1"
|
|
source = "https://www.anthropic.com/news/claude-sonnet-5"
|
|
date = "2026-06-30"
|
|
|
|
[[benchmarks]]
|
|
name = "OSWorld-Verified"
|
|
score = 81.2
|
|
metric = "success rate"
|
|
source = "https://www.anthropic.com/news/claude-sonnet-5"
|
|
date = "2026-06-30"
|
|
|
|
[[benchmarks]]
|
|
name = "BrowseComp"
|
|
score = 84.7
|
|
metric = "accuracy"
|
|
variant = "single agent"
|
|
source = "https://www.anthropic.com/news/claude-sonnet-5"
|
|
date = "2026-06-30"
|
|
|
|
[[benchmarks]]
|
|
name = "FrontierCode"
|
|
score = 38.8
|
|
metric = "pass rate"
|
|
version = "v1"
|
|
source = "https://www.anthropic.com/news/claude-sonnet-5"
|
|
date = "2026-06-30"
|