#13
GPT-5.6 Luna
OpenAI · Proprietary · Reasoning · 1.05M context
71/ 100 composite
Released 2026-07-09
Benchmark Scores by Category
Coding
51.5
Knowledge
81.0
Reasoning
66.9
Agentic
84.8
Math
97.3
Multimodal
66.5
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$0.2
per 1M tokens
Output
$1.2
per 1M tokens
Value Score
55.5
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: