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
Grok 4
xAI
Tierfrontierfrontier
Release Date2026-02-052025-07-09
Context Window
400K
256K
Max Output
128K
8K
Input Price (/1M)
$1.75
$3
Output Price (/1M)
$14
$15
Arena Elo
1,480
1,410
MMLU
93%
87.5%
GPQA
81%
87.5%
MATH
96%
91.7%
HumanEval
93%
90%
SWE-bench
80%
48%
AIME
94%
72%
SimpleQA
58%
34.2%
Capabilitiesvision, tool-use, code, reasoning, agenticvision, tool-use, code, reasoning

Benchmark Comparison

GPT-5.3 Codex
Grok 4
Arena Elo
1,480
1,410
MMLU
93%
87.5%
GPQA
81%
87.5%
MATH
96%
91.7%
HumanEval
93%
90%
SWE-bench
80%
48%
AIME
94%
72%
SimpleQA
58%
34.2%
Cost Estimate

Cost Calculator

GPT-5.3 Codex
$23.63/mo$0.7875/day
Grok 4
$27.00/mo$0.9000/day
Try These Models
Try GPT-5.3 CodexTry Grok 4