List your company

Competitive Programming Agent Evaluation on ALE Bench

1,909.4Final PerformanceLeeroo
760.8241,059.0121,357.21,655.388Jan 29, 2026Feb 22, 2026Mar 19, 2026Apr 12, 2026May 7, 2026May 31, 2026Jun 25, 2026

Evaluation results

MethodLinks
LeerooModel=Gemini-2.5-pro2026.011,909.46.1914.8
ALE-AgentModel=Gemini-2.5-pro2026.011,879.36.81,003.3
ALE SequentialModel=Gemini-2.5-pro2026.011,19854.1111
RiVERBackbone=Qwen3-8B2026.0698777.5—
RiVERBackbone=GLM-Z1-9B-04142026.0696278.8—
Rank-uniformBackbone=Qwen3-8B2026.0696078.9—
Instance-NormBackbone=Qwen3-8B2026.0693580.1—
Rank-uniformBackbone=GLM-Z1-9B-04142026.0693180.2—
Instance-NormBackbone=GLM-Z1-9B-04142026.0692980.6—
Raw-BinaryBackbone=Qwen3-8B2026.0692680.9—
RS-GRPOBackbone=GLM-Z1-9B-04142026.0691681.6—
Raw-BinaryBackbone=GLM-Z1-9B-04142026.0691581.8—
RS-GRPOBackbone=Qwen3-8B2026.0690482.5—
Raw-GRPOBackbone=Qwen3-8B2026.0690382.5—
Raw-GRPOBackbone=GLM-Z1-9B-04142026.0688683.6—
Qwen3-8BBackbone=Qwen3-8B2026.0684586.4—
ALE one-shotModel=Gemini-2.5-pro2026.0183288.44.7
GLM-Z1-9B-0414Backbone=GLM-Z1-9B-04142026.0680588.2—