Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

Claude Code vs GPT-5.1 Codex High

Anthropic 🇺🇸

78.8

#29—

GPT-5.1 Codex High

OpenAI 🇺🇸

79.9

#26—

Category Comparison

Benchmark-by-Benchmark

coding

Benchmark	Claude Code	GPT-5.1 Codex High
SWE-bench Verified	72.7	—

agent

Benchmark	Claude Code	GPT-5.1 Codex High
GAIA	72	—
WebArena	35	—

math

Benchmark	Claude Code	GPT-5.1 Codex High
AIME 2025	—	96.7

Category Winners

coding

Claude Code

67.2

math

GPT-5.1 Codex High

79.9

agent

Claude Code

87.5

Claude Code vs GPT-5.1 Codex High — Benchmark Comparison | Neura Market