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
SpecGPT-4.1 nano
OpenAI
Claude Opus 4.6
Anthropic
Tiersmallfrontier
Release Date2025-04-142026-02-05
Context Window
1048K
200K
Max Output
33K
128K
Input Price (/1M)
$0.1
$5
Output Price (/1M)
$0.4
$25
Arena Elo
1,190
1,496
MMLU
72%
92.5%
GPQA—
91.3%
MATH—
97.6%
HumanEval
81.2%
97%
SWE-bench—
72.5%
Capabilitiestool-use, codevision, tool-use, code, extended-thinking, agentic

Benchmark Comparison

GPT-4.1 nano
Claude Opus 4.6
Arena Elo
1,190
1,496
MMLU
72%
92.5%
GPQA
N/A
91.3%
MATH
N/A
97.6%
HumanEval
81.2%
97%
SWE-bench
N/A
72.5%
Cost Estimate

Cost Calculator

GPT-4.1 nano
$0.75/mo$0.0250/day
Claude Opus 4.6
$45.00/mo$1.5000/day