wehub-resource-sync
84 lines
1.7 KiB
TOML
84 lines
1.7 KiB
TOML
name = "Fugu"
|
||
description = "Multi-agent model for routing expert agents across complex analytical tasks"
|
||
family = "fugu"
|
||
release_date = "2026-06-15"
|
||
last_updated = "2026-06-15"
|
||
attachment = true
|
||
reasoning = true
|
||
temperature = false
|
||
tool_call = true
|
||
structured_output = true
|
||
open_weights = false
|
||
|
||
[limit]
|
||
context = 1_000_000
|
||
|
||
[modalities]
|
||
input = ["text", "image"]
|
||
output = ["text"]
|
||
|
||
[[links]]
|
||
label = "Official model catalog"
|
||
url = "https://raw.githubusercontent.com/SakanaAI/fugu/refs/heads/main/configs/files/fugu.json"
|
||
type = "docs"
|
||
|
||
[[benchmarks]]
|
||
name = "SWE Bench Pro"
|
||
score = 59.0
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "Terminal Bench 2.1"
|
||
score = 80.2
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "LiveCodeBench"
|
||
score = 92.9
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "LiveCodeBench Pro"
|
||
score = 87.8
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "Humanity’s Last Exam"
|
||
score = 47.2
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "CharXiv Reasoning"
|
||
score = 85.1
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "GPQA Diamond"
|
||
score = 95.5
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "SciCode"
|
||
score = 60.1
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "τ3 Banking"
|
||
score = 21.7
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "Long Context Reasoning"
|
||
score = 74.7
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "MRCRv2"
|
||
score = 86.6
|
||
source = "https://console.sakana.ai/models"
|
||
|
||
[[benchmarks]]
|
||
name = "CTI-REALM"
|
||
score = 67.5
|
||
source = "https://console.sakana.ai/models"
|