#27OpenAI· released 2026-09-22

OpenAI: GPT-6 Luna.

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

View on OpenRouter ↗
Context
1.1M
Input $/1M
$0.10
Output $/1M
$0.50
Modality
file · image · text
Arena Elo
1492
LMArena — human blind votes
AA Index
59.0
Artificial Analysis composite
LiveBench
74.6
Contamination-resistant
GPQA
76.8%
Grad-level science reasoning
MMLU-Pro
79.4%
Broad knowledge
SWE-bench
68.2%
Real GitHub bugs (Verified)
Terminal-Bench
49.6%
Agentic shell tasks
ARC-AGI
7.9%
Abstract reasoning
Aider Polyglot
72.1%
Multi-language code editing
Speed
142 tok/s
Median output speed

Profile

OpenAI: GPT-6 Luna is OpenAI's entry at position #27 on the current aggregated leaderboard. Its strongest signals are real-world software engineering, unattended agentic work, very long context. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard