LLM Leaderboard · Proprietary

GPT-5.3 Codex benchmarks, pricing, and LLM comparison.

Compare GPT-5.3 Codex vs GPT, Claude, Gemini, DeepSeek, open-weight, and frontier AI models using public benchmark scores, token pricing, context window, and access details.

Open live LLM leaderboardOpen in app
Rank #29AskClash overall score: 40.9
$1.75 / $14.0Input and output token price, when published. Context: 400K.
API/OAuthBilling and access path cached for this model row.

GPT-5.3 Codex benchmark snapshot

AskClash combines public LLM benchmark cells into a weighted percentile score and penalizes missing coverage so narrow rows do not dominate better-measured models.

Overall40.9
Benchmark cells5
Context400K
CreatorOpenAI

GPT-5.3 Codex public benchmark scores

Cached benchmark values can include HLE, GPQA, SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, MCP Atlas, MMMU-Pro, ARC-AGI-2, Tau2, and model-specific coding or agent scores.

RWT

8.0 score

SWE-bench

85.0 score

SWE-Pro

56.8 score

Terminal-Bench

77.3 score

OSWorld

64.7 score

Tau2

86.0 score

GPT-5.3 Codex vs other AI models

Use these comparison links to evaluate GPT-5.3 Codex against nearby LLMs by benchmark score, price, context window, and provider.

Claude Mythos/Fable 5 vs GPT-5.3 CodexClaude Opus 4.8 (Adaptive) vs GPT-5.3 CodexGPT-5.5 xHigh vs GPT-5.3 CodexGLM-5.2 vs GPT-5.3 CodexClaude Opus 4.7 (Adaptive) vs GPT-5.3 CodexQwen3.7 Max vs GPT-5.3 CodexGPT-5.4 xHigh vs GPT-5.3 CodexKimi K2.7 Code vs GPT-5.3 Codex

Related AI and tech coverage

Cached AskClash article matches that can provide release, provider, benchmark, pricing, or market context around this model.

Quoting Romain Huet

A quote from Romain Huet Simon Willison’s Weblog Subscribe Sponsored by: Sonar — Now with SAST + SCA for secure, dependency-aware Agentic Engineering. SonarQube Advanced Security 25th April 2026 Since GPT-5.4, we’ve unified Codex and the main model into a single system, so there’s no separate coding line anymore. GPT-5.5 takes this further, with strong gains in agentic coding, computer use, and any task on a computer. — Romain Huet , confirming OpenAI won't release a GPT-5.5-Codex model Posted 2

Quoting OpenAI Codex base_instructions

Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query. - Tracking the history of the now-deceased OpenAI Microsoft AGI clause - 27th April 2026

Last cached leaderboard date: June 18, 2026. This model page is generated from the AskClash LLM Leaderboard cache and linked from the live leaderboard.