Cheese Dossier · CF-1.3

Qwen3.7 Max

qwen · Cheese #15· 6 signals · specialty multilingual · Proprietary

CHEESE INDEX
61.4
DEPTH
80.4
BALANCE
95.4
CONSENSUS
81.6
STABILITY
98.4
COVERAGE
85%
VALUE
12.27
I / O
$1.25 / $3.75
SPECIALTY
multilingual +40.8
BEST FIT
long_horizon 70.6

深度雷達

codingagentmathknowleinstrumultimmultilreason

實線=本模型 · 虛線=群體中位

芝士軸

coding59.6
agent64.2
horizon61.4

Cheese Index = 可用軸中位數;Balance = 三軸分歧小。

能力細節

swe ★80.4
gpqa ★92.4
hle ★41.4
mcp76.4
coding ★80.4
agent ★64.2
math ★82.0
knowledge ★71.7
instruction ★91.0
multilingual ★100.0
reasoning ★88.2

部署建議

中段指數:適合成本敏感路徑。優先看 Pareto/Value;用深度雷達找專長匹配,再與更高指數模型 A/B。

鄰近差分

vs GPT-5.5 Pro

coding
agent+4.6
horizon