List your company

Math on Math (test)

80.9AccuracyOPCD
31.39644.24857.169.952Dec 3, 2025Dec 14, 2025Dec 26, 2025Jan 7, 2026Jan 19, 2026Jan 31, 2026Feb 12, 2026

Evaluation results

MethodLinks
OPCDModel=Qwen3-8B2026.0280.980.8
Context Distill.Model=Qwen3-8B2026.0279.580.4
In-ContextModel=Qwen3-8B2026.0279—
Base ModelModel=Qwen3-8B2026.027581.3
wd1Backbone=Dream-7B, Seq Len=512, Zero-shot=true2025.1250.5—
ESPOBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.1250.3—
diffu-GRPOBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.1248.9—
DreamBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.1248—
wd1Backbone=Dream-7B, Seq Len=256, Zero-shot=true2025.1247.4—
ESPOBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.1247.4—
diffu-GRPOBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.1246.9—
ESPOBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.1246—
wd1Backbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.1245.8—
DreamBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.1245.7—
diffu-GRPOBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.1245.1—
DreamBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.1244—
ESPOBackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.1243.4—
diffu-GRPOBackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.1241.7—
LLaDABackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.1241.4—
ESPOBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.1240.3—
wd1Backbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.1239.8—
ESPOBackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.1239.5—
wd1Backbone=Dream-7B, Seq Len=128, Zero-shot=true2025.1239.5—
diffu-GRPOBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.1239.4—
ESPOBackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.1239—
DreamBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.1238.2—
diffu-GRPOBackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.1237.7—
wd1Backbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.1237.7—
LLaDABackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.1237—
wd1Backbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.1236.9—
diffu-GRPOBackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.1236.6—
ESPOBackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.1236—
LLaDABackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.1235.2—
diffu-GRPOBackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.1234.9—
LLaDABackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.1234.4—
wd1Backbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.1233.3—