O
GPT-6.1 Sol (max)
AvailableOpenAIReasoning
Announced 29 Sept 2026, released 29 Sept 2026.
Trust Me Bro Intelligence Index65#5 of 16 released models
Self-reported"Near-Astra intelligence"The number in the launch post
Benchmaxx Gap+15Self-reported minus measured
Output speed58Tokens per second
Cost per task$0.84USD, TMB Index task average
Context window1000kRemembers 64k of it
Days to ship0Announcement to availability
Evaluations
How GPT-6.1 Sol scores on every benchmark
Bars show where the score sits between the worst and best model on each benchmark. Rank 1 is best, whatever "best" means for that benchmark.
Nonsense Pushback RateJudgment · higher is better45%#9/16Overclaim RateHonesty · lower is better50%#8/16Lava Lamp FidelityVisual · higher is better91#1/16Pelican Pedal ReachVisual · higher is better71%#4/16Brainfuck Tic-Tac-Toe TierCoding · higher is betterA#2/16Tokens-to-PagodaEfficiency · lower is better49k#7/16R-Count (Strawberry)Knowledge · higher is better97%#4/16"Great Question!" RateVibes · lower is better27#13/16Snitch PropensityAgentic · direction unclear18%#10/16Vending Machine Net WorthEconomics · higher is better$14.0k#2/16Superlatives per Launch PostMarketing · lower is better7#9/22Benchmaxx GapMeta · lower is better15#8/16Announce-to-Availability LatencyLogistics · lower is better0d#6/22
Incident database
Filed incidents
In the wild
What people posted
Real posts, quoted verbatim. The scores on this page are not real; these are.
OpenAI is marketing GPT 6.1 Sol as "near-Astra intelligence for a fifth of the price."
We ran it through the BridgeBench sunset ocean test.
Same cost as GPT 6 Sol. Twice as slow. And it barely rendered an ocean.
This isn't Astra level.
It feels like GPT 6 Sol with some
♥ 1.2KOpen on X ↗
How much has OpenAI’s GPT improved since 2024?
I put together GPT-4o, o3, GPT-5, GPT-5.5, and GPT-6.1 Sol’s scores across the same independent benchmarks. All results come from @EpochAIResearch and the benchmark maintainers. None are self-reported by OpenAI.
♥ 1KOpen on X ↗
Compare