OpenAI

GPT-5.6 Sol

Intelligence
42.3
Rank 51 of 788 measured models
Coding
77.2
Rank 7 of 301 measured models
Output speed
89.7 t/s
Rank 209 of 454 measured models
Price/1M
$8
Rank 673 of 741 measured models
Context window
1M
Rank 107 of 1334 measured models
Cost per task
$0.808
Rank 134 of 235 measured models

GPT-5.6 Sol (High) scores 42.3 on the Artificial Analysis Intelligence Index, ranking 51st of 788 measured models. The closest models on this index are Muse Wonder (43.6), Claude Opus 4.8 (batch) (41.8), and Ling 3.1 Flash (41.1). At $8 per million tokens (3:1 input/output blended price), it is priced close to Muse Wonder ($8), more expensive than Claude Opus 4.8 (batch) ($5) and Ling 3.1 Flash ($0.45). With an output speed of 89.7 t/s, it is faster than Ling 3.1 Flash (81.9 t/s), slower than Muse Wonder (113 t/s).

Artificial Analysis Indices
High
Intelligence42.3
Rank 51 of 788 measured models
Coding77.2
Rank 7 of 301 measured models
Agentic44.2
Rank 32 of 191 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 & Accounting45.8
Rank 58 of 260 measured models
Strategy & Ops50.6
Rank 53 of 260 measured models
Legal47.3
Rank 51 of 260 measured models
Healthcare & Medical42.9
Rank 47 of 190 measured models
Engineering43.0
Rank 59 of 259 measured models
Economics49.8
Rank 47 of 267 measured models
Standard Benchmarks
GPQA Diamond92.8%
Rank 28 of 621 measured models
HLE46.0%
Rank 49 of 682 measured models
SciCode57.8%
Rank 26 of 249 measured models
IFBench69.2%
Rank 75 of 451 measured models
AA-LCR81.7%
Rank 55 of 593 measured models
TerminalBench Hard62.1%
Rank 5 of 432 measured models
Terminal-Bench 2.187.3%
Rank 20 of 246 measured models
Terminal-Bench 4.020.7%
Rank 79 of 246 measured models
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