List your company

General Evaluation on Aggregate Benchmarks

93.9Average ScoreGemini 2.5 Pro+ASP
21.51640.30859.177.892Mar 4, 2026Mar 15, 2026Mar 27, 2026Apr 7, 2026Apr 19, 2026Apr 30, 2026May 12, 2026

Evaluation results

MethodLinks
Gemini 2.5 Pro+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0493.9
Gemini 2.5 Flash+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0486.9
o4-mini+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0482.3
DS-R1-0528+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0481.9
GOLFModel Backbone=Qwen-3-8B2026.0369.26
Rubric-as-RewardModel Backbone=Qwen-3-8B2026.0367.08
Pairwise-GRPOModel Backbone=Qwen-3-8B2026.0366.97
Critique-GRPOModel Backbone=Qwen-3-8B2026.0366.96
o4-miniInference Pipeline=Baseline2026.0463.4
Direct-LikertModel Backbone=Qwen-3-8B2026.0362.99
Gemini 2.5 ProInference Pipeline=Baseline2026.0462.9
Qwen-3-8BModel Backbone=Qwen-3-8B2026.0353.95
DS-R1-0528Inference Pipeline=Baseline2026.0452.3
δ-MemBackbone=Qwen3-4B-Instruct, Memory Configuration=TSW2026.0551.66
δ-MemBackbone=Qwen3-4B-Instruct, Memory Configuration=SSW2026.0551.44
δ-MemBackbone=Qwen3-8B, Memory Configuration=SSW2026.0550.86
δ-MemBackbone=Qwen3-8B, Memory Configuration=MSW2026.0550.84
δ-MemBackbone=Qwen3-4B-Instruct, Memory Configuration=MSW2026.0550.74
δ-MemBackbone=Qwen3-8B, Memory Configuration=TSW2026.0550.68
GOLFModel Backbone=Llama-3.1-8B-Instruct2026.0350.19
Qwen3-8BBackbone=Qwen3-8B2026.0547.2
Qwen3-4B-InstructBackbone=Qwen3-4B-Instruct2026.0546.79
Context2LoRABackbone=Qwen3-8B2026.0545.92
DS-V3+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0445
Context2LoRABackbone=Qwen3-4B-Instruct2026.0544.9
Gemini 2.5 FlashInference Pipeline=Baseline2026.0443.3
Critique-GRPOModel Backbone=Llama-3.1-8B-Instruct2026.0340.92
Rubric-as-RewardModel Backbone=Llama-3.1-8B-Instruct2026.0340.11
Pairwise-GRPOModel Backbone=Llama-3.1-8B-Instruct2026.0339.94
δ-MemBackbone=SmolLM3-3B, Memory Configuration=MSW2026.0536.96
δ-MemBackbone=SmolLM3-3B, Memory Configuration=SSW2026.0536.67
Direct-LikertModel Backbone=Llama-3.1-8B-Instruct2026.0335.79
Context2LoRABackbone=SmolLM3-3B2026.0534.94
δ-MemBackbone=SmolLM3-3B, Memory Configuration=TSW2026.0534.74
DS-V3Inference Pipeline=Baseline2026.0434.3
SmolLM3-3BBackbone=SmolLM3-3B2026.0526.08
Llama-3.1-8B-InstructModel Backbone=Llama-3.1-8B-Instruct2026.0324.3