GPT-6 Luna: benchmarks, price and rank
GPT-6 Luna from OpenAI is 58th of 123 rated AI models on Spezia's leaderboard. It costs $0.10 in, $0.50 out per million tokens.
- 58th of 123 rated models
- Rating 1,273
- Rated on 9 benchmarks
- Closed
- Released Sep 22, 2026
- 1.1 million tokens of context
- Knows the world to May 2026
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 92nd of 107 on LMArena text
- 42nd of 56 on APEX-Agents
- 17th of 27 on DeepSWE 1.1
Price: $0.10 in, $0.50 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- APEX-Agents44.3%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
42nd of 56. Independent result from Epoch AI.
- DeepSWE 1.166.6%
Software engineering tasks run in the same simple agent setup for every model.
17th of 27. The maker's own number, from OpenAI, via LLM Stats.
- SimpleQA Verified41.4%
Short factual questions with one checked answer, asked without web search.
47th of 78. Independent result from Epoch AI.
- FrontierMath79.0%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
21st of 76. Independent result from Epoch AI.
- LMArena text1,388
People put a question to two anonymous models and vote for the better answer.
92nd of 107. Independent result from LMArena.
- LMArena WebDev1,577
People ask two anonymous models to build the same web page or app and vote for the better one.
35th of 98. Independent result from LMArena.
- GPQA Diamond90.5%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
43rd of 103. Independent result from Epoch AI.
- ARC-AGI-259.3%
Visual puzzles of colored grids, each with a new rule to work out from a few examples.
37th of 69. Independent result from Epoch AI.
- FrontierMath Tier 456.1%
Research-level problems that take professional mathematicians days.
22nd of 66. Independent result from Epoch AI.
- Epoch Capabilities Index156.4
One score built from dozens of benchmarks, set on a common scale so that models tested on different benchmarks can still be compared.
34th of 94. Independent result from Epoch AI.
Its full profile is in Spezia.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.