LLM Comparison

GPT-5.5 vs GPT-5.3 Codex: benchmark scores, pricing & comparison.

Side-by-side GPT-5.5 vs GPT-5.3 Codex comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.

Open live leaderboardGPT-5.5 model pageGPT-5.3 Codex model page
Rank #7 vs #27AskClash overall scores 72.8 vs 43.4.
Pricing $5.00/$30.0 vs $1.75/$14.0Input and output token prices per 1M tokens when published.
Proprietary vs ProprietaryOpenAI vs OpenAI.

GPT-5.5 vs GPT-5.3 Codex benchmark comparison

Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.

MetricGPT-5.5GPT-5.3 Codex
Overall Score72.843.4
Leaderboard Rank#7#27
RWT8.08.0
Coding Agent Index61.5—
HLE52.2—
GPQA93.6—
SWE-bench—85.0
SWE-Pro58.656.8
Terminal-Bench82.777.3
DeepSWE67.0—
OSWorld78.764.7
MCP Atlas75.3—
Finance Agent51.8—
MMMU-Pro81.2—
ARC-AGI 285.0—
Tau298.086.0
Input Price (per 1M tokens)$5.00$1.75
Output Price (per 1M tokens)$30.0$14.0
Context Window1M400K
Benchmarks Published145

GPT-5.5 vs GPT-5.3 Codex head-to-head charts

GPT-5.5 leads 5 and GPT-5.3 Codex leads 0 of 6 shared benchmarks. GPT-5.3 Codex is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

GPT-5.5GPT-5.3 Codex
Overall
72.8GPT-5.5
43.4GPT-5.3 Codex
RWT
8.0GPT-5.5
8.0GPT-5.3 Codex
SWE-Pro
58.6GPT-5.5
56.8GPT-5.3 Codex
Terminal-Bench
82.7GPT-5.5
77.3GPT-5.3 Codex
OSWorld
78.7GPT-5.5
64.7GPT-5.3 Codex
Tau2
98.0GPT-5.5
86.0GPT-5.3 Codex
GPT-5.5
Input$5.00
Output$30.0
Workload$11
Context1M
GPT-5.3 Codex
Input$1.75
Output$14.0
Workload$4.55
Context400K

Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.

More GPT-5.5 and GPT-5.3 Codex comparisons

Explore how GPT-5.5 and GPT-5.3 Codex stack up against other top-ranked LLMs.

Claude Opus 5 vs GPT-5.5Claude Opus 5 vs GPT-5.3 CodexClaude Fable 5 vs GPT-5.5Claude Fable 5 vs GPT-5.3 CodexGPT-5.6 Sol vs GPT-5.5GPT-5.6 Sol vs GPT-5.3 CodexKimi K3 vs GPT-5.5Kimi K3 vs GPT-5.3 CodexQwen3.8 Max vs GPT-5.5Qwen3.8 Max vs GPT-5.3 Codex

How to read this comparison

Benchmark scores

Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.

Token pricing

Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.

Coverage matters

Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.

This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.