name = "GPT-5-Codex"
description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work"
family = "gpt-codex"
release_date = "2025-09-15"
last_updated = "2025-09-15"
attachment = false
reasoning = true
temperature = false
tool_call = true
structured_output = true
knowledge = "2024-09-30"
open_weights = false

[limit]
context = 400_000
input = 272_000
output = 128_000

[modalities]
input = ["text", "image"]
output = ["text"]

[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 38.9
metric = "index"
source = "https://openrouter.ai/openai/gpt-5-codex/benchmarks"
date = "2026-06-01"

[[benchmarks]]
name = "SciCode"
score = 40.9
metric = "percent correct"
source = "https://openrouter.ai/openai/gpt-5-codex/benchmarks"
date = "2026-06-01"

[[benchmarks]]
name = "Terminal-Bench Hard"
score = 37.9
metric = "success rate"
source = "https://openrouter.ai/openai/gpt-5-codex/benchmarks"
date = "2026-06-01"