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
ProgramBench (Almost Solved)
Coding
Share
Results for 12 models collected from 6 public sources.
Ranking
Sources
#
Model
Score
1
Claude Opus 5
Anthropic
41.5
%
2
Claude Fable 5
Anthropic
33.0
%
3
Qwen4-Max
Alibaba
31.5
%
4
Hunyuan 4
Tencent
30.0
%
5
Qwen3.8-Max
Alibaba · 0902
28.0
%
6
GPT-5.6 Sol
OpenAI
23.0
%
7
DeepSeek-V4.1-Flash
DeepSeek
20.3
%
8
GLM-5.3
Zhipu AI
19.0
%
9
Kimi K3
Moonshot AI
17.5
%
10
Hunyuan 4 flash
Tencent
16.0
%
12 models total
1
2