List your company

Accuracy on Long-context Understanding on LongBench

103AccuracyQUOKA
35.81653.25870.788.142Feb 9, 2026

Evaluation results

MethodLinks
QUOKAModel=Smollm3, Budget (BSA)=10242026.02103
QUOKAModel=Smollm3, Budget (BSA)=20482026.02102.8
QUOKAModel=Smollm3, Budget (BSA)=5122026.0299.8
QUOKAModel=Qwen3-4B, Budget (BSA)=20482026.0299.5
QUOKAModel=Qwen3-4B, Budget (BSA)=10242026.0299.2
QUOKAModel=Llama3.2-3B-Instruct, Budget (BSA)=20482026.0298.6
QUOKAModel=Qwen2.5-3B-Instruct, Budget (BSA)=20482026.0297.7
QUOKAModel=Llama3.2-3B-Instruct, Budget (BSA)=10242026.0297.2
QUOKAModel=Qwen3-4B, Budget (BSA)=5122026.0296.6
SampleAttnModel=Smollm3, Budget (BSA)=20482026.0296.6
SampleAttnModel=Qwen3-4B, Budget (BSA)=20482026.0294.7
QUOKAModel=Llama3.2-3B-Instruct, Budget (BSA)=5122026.0294.5
QUOKAModel=Qwen2.5-3B-Instruct, Budget (BSA)=10242026.0294.5
SampleAttnModel=Smollm3, Budget (BSA)=10242026.0292.9
SparQModel=Smollm3, Budget (BSA)=20482026.0292.2
LessIsMoreModel=Smollm3, Budget (BSA)=20482026.0291.8
SampleAttnModel=Llama3.2-3B-Instruct, Budget (BSA)=20482026.0290.1
SampleAttnModel=Qwen3-4B, Budget (BSA)=10242026.0287.5
SparQModel=Qwen3-4B, Budget (BSA)=20482026.0287.2
LokiModel=Qwen3-4B, Budget (BSA)=20482026.0287.2
QUOKAModel=Qwen2.5-3B-Instruct, Budget (BSA)=5122026.0286.9
LessIsMoreModel=Qwen3-4B, Budget (BSA)=20482026.0286.8
SampleAttnModel=Smollm3, Budget (BSA)=5122026.0285.6
LessIsMoreModel=Llama3.2-3B-Instruct, Budget (BSA)=20482026.0285
SparQModel=Llama3.2-3B-Instruct, Budget (BSA)=20482026.0284.2
LokiModel=Llama3.2-3B-Instruct, Budget (BSA)=20482026.0284.2
LessIsMoreModel=Smollm3, Budget (BSA)=10242026.0284.2
SampleAttnModel=Qwen2.5-3B-Instruct, Budget (BSA)=20482026.0282.8
SparQModel=Qwen2.5-3B-Instruct, Budget (BSA)=20482026.0280.8
SparQModel=Smollm3, Budget (BSA)=10242026.0280.5
SparQModel=Llama3.2-3B-Instruct, Budget (BSA)=10242026.0280.2
LokiModel=Smollm3, Budget (BSA)=10242026.0280.1
SampleAttnModel=Llama3.2-3B-Instruct, Budget (BSA)=10242026.0280
LessIsMoreModel=Llama3.2-3B-Instruct, Budget (BSA)=10242026.0278.8
LokiModel=Qwen2.5-3B-Instruct, Budget (BSA)=20482026.0278.7
SparQModel=Qwen3-4B, Budget (BSA)=10242026.0278.2
LokiModel=Qwen3-4B, Budget (BSA)=10242026.0278.2
LessIsMoreModel=Qwen3-4B, Budget (BSA)=10242026.0277.3
LessIsMoreModel=Smollm3, Budget (BSA)=5122026.0276.5
LokiModel=Llama3.2-3B-Instruct, Budget (BSA)=10242026.0275.7
SampleAttnModel=Qwen2.5-3B-Instruct, Budget (BSA)=10242026.0275.6
SampleAttnModel=Qwen3-4B, Budget (BSA)=5122026.0275.5
SampleAttnModel=Llama3.2-3B-Instruct, Budget (BSA)=5122026.0273.8
SparQModel=Qwen2.5-3B-Instruct, Budget (BSA)=10242026.0272.6
SparQModel=Smollm3, Budget (BSA)=5122026.0272.5
SparQModel=Llama3.2-3B-Instruct, Budget (BSA)=5122026.0272.1
LessIsMoreModel=Llama3.2-3B-Instruct, Budget (BSA)=5122026.0270.3
LokiModel=Llama3.2-3B-Instruct, Budget (BSA)=5122026.0268.6
SparQModel=Qwen3-4B, Budget (BSA)=5122026.0268.6
LokiModel=Qwen2.5-3B-Instruct, Budget (BSA)=10242026.0267.1
LessIsMoreModel=Qwen3-4B, Budget (BSA)=5122026.0266.5
SampleAttnModel=Qwen2.5-3B-Instruct, Budget (BSA)=5122026.0266
LessIsMoreModel=Qwen2.5-3B-Instruct, Budget (BSA)=20482026.0265.9
SparQModel=Qwen2.5-3B-Instruct, Budget (BSA)=5122026.0263.6
LokiModel=Qwen3-4B, Budget (BSA)=5122026.0262.2
LokiModel=Smollm3, Budget (BSA)=20482026.0262.2
LokiModel=Qwen2.5-3B-Instruct, Budget (BSA)=5122026.0258.9
LessIsMoreModel=Qwen2.5-3B-Instruct, Budget (BSA)=10242026.0255.6
LessIsMoreModel=Qwen2.5-3B-Instruct, Budget (BSA)=5122026.0246.1
LokiModel=Smollm3, Budget (BSA)=5122026.0238.4