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
SpecDeepSeek V3.2
DeepSeek
Claude Opus 4.6
Anthropic
Tieropenfrontier
Release Date2025-12-012026-02-05
Context Window
131K
200K
Max Output
131K
128K
Input Price (/1M)
$0.28
$5
Output Price (/1M)
$0.42
$25
Arena Elo
1,419
1,496
MMLU
85.7%
92.5%
GPQA
79.9%
91.3%
MATH—
97.6%
HumanEval
92%
97%
SWE-bench
52%
72.5%
Capabilitiestool-use, codevision, tool-use, code, extended-thinking, agentic

Benchmark Comparison

DeepSeek V3.2
Claude Opus 4.6
Arena Elo
1,419
1,496
MMLU
85.7%
92.5%
GPQA
79.9%
91.3%
MATH
N/A
97.6%
HumanEval
92%
97%
SWE-bench
52%
72.5%
Cost Estimate

Cost Calculator

DeepSeek V3.2
$1.05/mo$0.0350/day
Claude Opus 4.6
$45.00/mo$1.5000/day