Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Benchmark details loading
Back to benchmarks
Agentic IF Index (Internal)
Agents
Share
Meta internal instruction-following benchmark; the source chart does not publish a reproducible methodology.
Ranking
Sources
#
Model
Score
1
GPT-5.6 Sol
OpenAI · max mode
60.5
%
2
Claude Opus 5
Anthropic · max mode
59.1
%
3
Muse Spark 1.3
Meta · max mode
57.8
%
4
Muse Spark 1.2
Meta · xhigh mode
46.2
%
4 models total
