GPT-6 Luna

Proprietarygeneralcodingfastbudget

Leaderboard Score

51.2

Scale: 0 - 100

Throughput Speed

157 tps

Context Window

1.1M

API Pricing / 1M

$0.10

Parameter Scale

Proprietary

Verified AI Radar & Benchmarks•8 Evaluated Metrics

Capability Radar & Benchmark Scores

Multi-Axis Capability Radar

Comparing GPT-6 Luna against Frontier Top 10 & Open-Source average

0 - 100 Scale

GPT-6 Luna

Frontier Top 10 Avg

Open-Source Avg

Performance Vectors

Where GPT-6 Luna Leads

Coding & SWETop 10: 79.1% • OS: 47.6%

72.4%-6.7% vs Top 10

Reasoning & MathTop 10: 74.6% • OS: 46.6%

62.0%-12.6% vs Top 10

Agent & Tool AutomationTop 10: 71.2% • OS: 31.9%

42.1%-29.1% vs Top 10

Terminal & CLI ExecutionTop 10: 80.4% • OS: 47.6%

71.0%-9.4% vs Top 10

MMLU & Knowledge QATop 10: 50% • OS: 86.7%

64.0%+14.0% vs Top 10

Cyber & Security ExploitsTop 10: 87.8% • OS: 80.6%

48.6%-39.2% vs Top 10

All Verified Benchmark Evaluations

Direct Pass@1 and resolution rates across standardized evaluations.

CodingReasoningAgenticMath

Featured Compute Platform

Run Benchmarks on Dedicated AI Clusters

Zero-cold-start inference endpoints with dedicated GPU instances.

Compare With Alternatives →

Executive Analysis & Verdict

GPT-6 Luna by OpenAI is an ultra-fast, budget-optimized coding and reasoning model delivering 157 tps, 1.1M context, and the lowest cost-per-task ($0.068) on Artificial Analysis.

Key Strengths & Highlights

•Lowest cost per Intelligence Index task ($0.068) in the frontier class
•Blazing 157 tps throughput with sub-250ms time-to-first-token latency
•Strong 72.4% SWE-bench coding accuracy at just $0.10 per 1M input tokens

Limitations & Considerations

•Not intended for maximum-difficulty math proofs or doctoral-level formal logic

Recommended Workflows

High-volume code generation, CI/CD automated review bots, customer-facing agents, and economical developer workflows

The High-Speed, Ultra-Budget Frontier Workhorse

OpenAI’s GPT-6 Luna is engineered for extreme efficiency. At only $0.10 per million input tokens and 157 tokens per second, it provides accessible frontier performance for high-frequency agentic loops and production deployments.

Key Specifications

Provider: OpenAI
License / Weights: Proprietary
Context Window: 1,050,000 tokens (1.1M)
Max Output: 128,000 tokens
Inference Speed: 157 tps
API Pricing: $0.10 / 1M input tokens ($0.50 / 1M output tokens, $0.01 cache read)

Benchmark Highlights

Overall Score: 51.2 / 100
Artificial Analysis Intelligence Index: 37.3
AA-Briefcase Elo: 1299
SWE-bench Verified: 72.4%
GPQA Diamond: 62.0%
MATH-500: 66.5%
Terminal-Bench: 71.0%

Frequently Asked Questions About GPT-6 Luna

What is GPT-6 Luna and who developed it?↓

GPT-6 Luna is a proprietary large language model developed by OpenAI. It ranks #34 on the RankLLMs composite leaderboard, ahead of 61% of the 85 models we track, with an overall score of 51.2 / 100.

What context window and inference speed does GPT-6 Luna offer?↓

GPT-6 Luna supports a NaNK-token input context window and generates about 157 tps tokens per second in our reference measurements and suitable for extended reasoning sessions and multi-turn agent workflows..

Why is GPT-6 Luna priced so far below its peers?↓

GPT-6 Luna is cheaper than 88% of the priced models we track at $0.10 per 1M tokens, while keeping competitive benchmark scores - which is why it rates well on cost per solved task, not just per token.

What is GPT-6 Luna best at?↓

GPT-6 Luna is strongest in Lowest cost per Intelligence Index task ($0.068) in the frontier class; Blazing 157 tps throughput with sub-250ms time-to-first-token latency; Strong 72.4% SWE-bench coding accuracy at just $0.10 per 1M input tokens. Full pillar-by-pillar numbers are in the benchmark tables above.

What should you watch out for with GPT-6 Luna?↓

Known trade-offs include: Not intended for maximum-difficulty math proofs or doctoral-level formal logic. Weigh these against the strengths above for your specific workload.