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
GPT-5.2
OpenAI
Tierfrontierfrontier
Release Date2026-02-052025-12-11
Context Window
200K
400K
Max Output
128K
128K
Input Price (/1M)
$5
$1.75
Output Price (/1M)
$25
$14
Arena Elo
1,496
1,438
MMLU
92.5%
92.8%
GPQA
91.3%
90.3%
MATH
97.6%
98%
HumanEval
97%
97%
SWE-bench
72.5%
68%
Capabilitiesvision, tool-use, code, extended-thinking, agenticvision, tool-use, code, reasoning, agentic

Benchmark Comparison

Claude Opus 4.6
GPT-5.2
Arena Elo
1,496
1,438
MMLU
92.5%
92.8%
GPQA
91.3%
90.3%
MATH
97.6%
98%
HumanEval
97%
97%
SWE-bench
72.5%
68%
Cost Estimate

Cost Calculator

Claude Opus 4.6
$45.00/mo$1.5000/day
GPT-5.2
$23.63/mo$0.7875/day