GPT-6.2 Sol vs GPT-5.6 Luna

Source-checked evaluation entries, evidence gaps and checked price quotes where available.

GPT-6.2 Sol

OpenAI
Text Arena1465 ± 12

GPT-6.2 Sol (Max). Board 2026-11-20; checked 2026-11-22.

Composite / MMLU estimatesWithheld
Standard short-context input quote / 1M tokens$2

OpenAI pricing · checked 2026-11-22. Context tiers and cache-hit rates may differ.

GPT-5.6 Luna

OpenAI
Text Arena1453 ± 4

GPT-5.6 Luna (xHigh). Board 2026-11-20; checked 2026-11-22.

Composite / MMLU estimatesWithheld
Standard short-context input quote / 1M tokens$0.2

OpenAI pricing · checked 2026-11-22. Context tiers and cache-hit rates may differ.

What the evidence supports

The recorded entries are GPT-6.2 Sol (Max) (1465 ± 12) and GPT-5.6 Luna (xHigh) (1453 ± 4).

Their point estimates differ by 12 points. The displayed ranges overlap; this is not a test of task-specific superiority or a guarantee about a different configuration.

The former composite, MMLU and cost-per-capability recommendations are withdrawn because their inputs included unsupported estimates. No upgrade or overall capability recommendation is made from those numbers.

In the selected standard short-context input quotes, GPT-5.6 Luna has the lower rate, by a ratio of 10 to one. DeepSeek uses peak pricing. This is input pricing only; it does not estimate a whole workload or establish account access.

Price quotes are from the selected provider registry checked 2026-11-22. Unverified legacy quotes are withheld. Use the token calculator for input, output, cache-hit and context-tier scenarios. Additional service charges and account-specific terms can change a bill. Missing pricing evidence does not mean free inference.

Reporting on OpenAI