Model Horizon
DashboardModelsCompare
© 2026 Model Horizon
About|Terms
SYS.v0.1.0
Skip to content
  1. Home
  2. /Compare

Compare Models

Side-by-side comparison of AI model specs, benchmarks, and pricing.

Swap
Specifications
SpecClaude Opus 4.6
Anthropic
Claude Sonnet 4.5
Anthropic
Tierfrontierfrontier
Release Date2026-02-052025-09-29
Context Window
200K
200K
Max Output
128K
64K
Input Price (/1M)
$5
$3
Output Price (/1M)
$25
$15
Arena Elo
1,496
1,450
MMLU
92.5%
88.7%
GPQA
91.3%
83.4%
MATH
97.6%
87%
HumanEval
97%
95%
SWE-bench
72.5%
55.8%
Capabilitiesvision, tool-use, code, extended-thinking, agenticvision, tool-use, code, extended-thinking

Benchmark Comparison

Claude Opus 4.6
Claude Sonnet 4.5
Arena Elo
1,496
1,450
MMLU
92.5%
88.7%
GPQA
91.3%
83.4%
MATH
97.6%
87%
HumanEval
97%
95%
SWE-bench
72.5%
55.8%
Cost Estimate

Cost Calculator

Claude Opus 4.6
$45.00/mo$1.5000/day
Claude Sonnet 4.5
$27.00/mo$0.9000/day