Back

OpenAI

GPT-6.1 Sol

ReasoningClosed weightsModels.dev
Intelligence
51.8
Rank 13 of 744 measured models
Output speed
47.9 t/s
Rank 325 of 403 measured models
Price/1M
$4
Rank 532 of 659 measured models
Context window
1M
Rank 84 of 1199 measured models
Cost per task
$0.724
Rank 116 of 193 measured models

GPT-6.1 Sol (Max) scores 51.8 on the Artificial Analysis Intelligence Index, ranking 13th of 744 measured models. The closest models on this index are GPT-6 Astra (52.7), Gemini 4 Argon (High) (52.6), and Muse Wonder (Max) (52.4). At $4 per million tokens (3:1 input/output blended price), it is cheaper than GPT-6 Astra ($20) and Muse Wonder (Max) ($8), priced close to Gemini 4 Argon (High) ($4). With an output speed of 47.9 t/s, it is faster than GPT-6 Astra (43.9 t/s), slower than Muse Wonder (Max) (131 t/s).

Artificial Analysis Indices
Maximum
Intelligence51.8
Rank 13 of 744 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Cost per task
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting54.0
Rank 13 of 218 measured models
Strategy & Ops57.0
Rank 10 of 218 measured models
Legal57.7
Rank 12 of 218 measured models
Healthcare & Medical51.2
Rank 9 of 82 measured models
Engineering53.9
Rank 13 of 217 measured models
Economics59.3
Rank 16 of 225 measured models
Decision Index
GPT-6.1 Sol (Max) · Artificial Analysis
Decision Index70.9Rank 4 of 26 measured models
AA-Omniscience-Decision · accuracy91.0
AA-Omniscience-Decision · non-hallucination11.1
HLE-MultiChoice58.9
When2Call81.2
WildGuardTest92.5
Cost per 1M tasks$6,322.89
Average time per task4.43 s
Standard Benchmarks
HLE52.9%
Rank 18 of 664 measured models
SciCode54.2%
Rank 63 of 231 measured models
AA-LCR83.0%
Rank 25 of 575 measured models
Terminal-Bench v456.1%
Rank 10 of 218 measured models
Additional benchmarks6
Design Arena · 3d71.8%
Design Arena · Codecategories58.0%
Design Arena · Dataviz57.4%
Design Arena · Gamedev61.0%
Design Arena · Uicomponent57.8%
Design Arena · Website55.7%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy