Model Horizon
DashboardModelsCompareBenchmarks
© 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-5.3 Codex
OpenAI
Claude Opus 4.6
Anthropic
Tierfrontierfrontier
Release Date2026-02-052026-02-05
Context Window
400K
200K
Max Output
128K
128K
Input Price (/1M)
$1.75
$5
Output Price (/1M)
$14
$25
Arena Elo
1,480
1,496
MMLU
93%
92.5%
GPQA
81%
91.3%
MATH
96%
97.6%
HumanEval
93%
97%
SWE-bench
80%
72.5%
AIME
94%
83.3%
SimpleQA
58%
43.2%
Capabilitiesvision, tool-use, code, reasoning, agenticvision, tool-use, code, extended-thinking, agentic

Benchmark Comparison

GPT-5.3 Codex
Claude Opus 4.6
Arena Elo
1,480
1,496
MMLU
93%
92.5%
GPQA
81%
91.3%
MATH
96%
97.6%
HumanEval
93%
97%
SWE-bench
80%
72.5%
AIME
94%
83.3%
SimpleQA
58%
43.2%
Cost Estimate

Cost Calculator

GPT-5.3 Codex
$23.63/mo$0.7875/day
Claude Opus 4.6
$45.00/mo$1.5000/day
Try These Models
Try GPT-5.3 CodexTry Claude Opus 4.6