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
PostTrainBench v1.1
Coding
Agents
Share
Official website
Evaluates model post-training with OpenCode, a single NVIDIA H100 and a 10-hour budget. The score is a weighted aggregate across four base models and seven benchmarks.
Ranking
Sources
#
Model
Score
1
Claude Opus 5.5
Anthropic
49.3
%
2
Gemini 4 Argon
Google
45.3
%
3
GPT-6 Astra
OpenAI
44.3
%
4
Claude Fable 5.1
Anthropic
40.2
%
4 models total
