Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Claude 4 Opus (Extended Thinking)
Anthropic
Frontier Model
Reasoning
Vision Model
Proprietary
Context
Release Date
May 22, 2025
Knowledge Cutoff
Mar 01, 2025
Window
200k
Pricing
Per 1M tokens
Input
$15
Output
$75
Blended 3:1
$30
Capabilities
Speed
56 t/s
Input
Output
Reasoning tokens
Latency
TTFT
2.85 ms
500 token response
47.85 s
Benchmarks
Reasoning
●●●○○
Math
●●●●○
Coding
●●●○○
MMLU Pro
87.3%
GPQA
79.6%
HLE
11.7%
SciCode
39.8%
AIME
75.7%
MATH 500
98.2%
LiveCodeBench
63.6%