Benched.ai
View
About
Command Palette
Search for a command to run...
Models
DeepSeek R1 (Jan '25)
DeepSeek
Frontier Model
Reasoning
Open
Context
Release Date
Jan 20, 2025
Window
128k
Pricing
Per 1M tokens
Input
$1.675
Output
$3.5
Blended 3:1
$2.3625
Capabilities
Input
Output
Reasoning tokens
Benchmarks
Reasoning
●●●○○
Math
●●●●○
Coding
●●○○○
MMLU Pro
84.4%
GPQA
70.8%
HLE
9.3%
SciCode
35.7%
AIME
68.3%
MATH 500
96.6%
LiveCodeBench
61.7%
HumanEval
97.7%