GPT-5.6

OpenAI llm

Introduces durable capability tiers named Sol, Terra and Luna in place of the earlier Instant and Thinking naming. Scores are for the flagship Sol tier.

overall ⌄

72.5

12 of 125 ranked

price · $/M tokens

5 / 30

in / out, as of 2026-07-25

to run it yourself ⌄

API only

no weights to run

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmarkpublishedmeasured
GPQA94.6 94.1
SWE-bench Pro64.6 —
BrowseComp90.4 —

Cheaper, and at least as good

On a 1,000-in, 1,000-out call these cost less and rank no lower — a hard comparison to argue with, and a narrow one. Value covers what it misses.

Claude Sonnet 5.5 Anthropic$0.0120overall 72.7
GPT-5.2 OpenAI$0.0158overall 73.6
Claude Opus 5.5 Anthropic$0.0240overall 75.0
Claude Opus 4.7 Anthropic$0.0300overall 72.6
Claude Opus 4.8 Anthropic$0.0300overall 76.4

Lineage

No recorded lineage — root or standalone model.

view in full graph →

Metadata

orgOpenAI
released2026-07-09
licenseproprietary