MDL
GPT-5.3 Codex
OpenAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
94
percentile index
Price /M
$1.75 / $14
in / out
Context
400K
tokens
Avg score
67.6
7 benchmarks
AA Intelligence
44.3
index
Speed
99 tok/s
TTFT 54s
Released
Feb 5, 2026
About
GPT-5.3 Codex is a proprietary model in the GPT family from OpenAI. Benchmarked on 7 evals, averaging 67.6.
Benchmark scores · 7
avg 67.6 — higher is betterThe research behind this model
all papers mentioning it →SCDBench: A Benchmark for LLM-Based Smart Contract DecompilersMay 27, 2026LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt InjectionMay 18, 2026HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM PoolsMay 16, 2026Agent Island: A Saturation- and Contamination-Resistant Benchmark from Multiagent GamesMay 5, 2026Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?May 4, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed99 tok/s
Latency (TTFT)54s
Price in / out$1.75 / $14 per 1M
Blended price$4.81 / 1M
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$14/M