List your company
ResearchFormerly WizWand

Latency Measurement for Long-context reasoning on OOLONG

7.1Latency (s)Direct
-3.9870.81145.6220.39Mar 20, 2026
Updated 7mo ago

Evaluation results

MethodLinks
DirectParadigm=P1: Direct, Backbone=Mistral, Model Size=7B2026.037.1
DirectParadigm=P1: Direct, Backbone=Llama, Model Size=8B2026.037.9
DirectParadigm=P1: Direct, Backbone=Qwen3, Model Size=8B2026.038.4
DirectParadigm=P1: Direct, Backbone=Mistral, Model Size=Cdsrl2026.0312.6
DirectParadigm=P1: Direct, Backbone=Qwen3, Model Size=32B2026.0314.2
DirectParadigm=P1: Direct, Backbone=Mistral, Model Size=8x22B2026.0315.4
DirectParadigm=P1: Direct, Backbone=Llama, Model Size=70B2026.0316.1
DirectParadigm=P1: Direct, Backbone=Qwen3, Model Size=235B2026.0335.8
λ-RLMParadigm=P3: λ-RLM, Backbone=Llama, Model Size=405B2026.0338.5
DirectParadigm=P1: Direct, Backbone=Llama, Model Size=405B2026.0340.3
λ-RLMParadigm=P3: λ-RLM, Backbone=Qwen3, Model Size=235B2026.0342.3
λ-RLMParadigm=P3: λ-RLM, Backbone=Mistral, Model Size=Cdsrl2026.0348.1
λ-RLMParadigm=P3: λ-RLM, Backbone=Llama, Model Size=70B2026.0348.2
λ-RLMParadigm=P3: λ-RLM, Backbone=Qwen3, Model Size=32B2026.0351.7
λ-RLMParadigm=P3: λ-RLM, Backbone=Mistral, Model Size=8x22B2026.0356.4
λ-RLMParadigm=P3: λ-RLM, Backbone=Qwen3, Model Size=8B2026.0362.4
λ-RLMParadigm=P3: λ-RLM, Backbone=Llama, Model Size=8B2026.0366.8
λ-RLMParadigm=P3: λ-RLM, Backbone=Mistral, Model Size=7B2026.0371.5
RLMParadigm=P2: RLM, Backbone=Llama, Model Size=405B2026.03108.2
RLMParadigm=P2: RLM, Backbone=Qwen3, Model Size=235B2026.03125.7
RLMParadigm=P2: RLM, Backbone=Mistral, Model Size=Cdsrl2026.03168.7
RLMParadigm=P2: RLM, Backbone=Llama, Model Size=70B2026.03182.5
RLMParadigm=P2: RLM, Backbone=Qwen3, Model Size=32B2026.03198.3
RLMParadigm=P2: RLM, Backbone=Mistral, Model Size=8x22B2026.03215.3
RLMParadigm=P2: RLM, Backbone=Qwen3, Model Size=8B2026.03241.6
RLMParadigm=P2: RLM, Backbone=Llama, Model Size=8B2026.03258.4
RLMParadigm=P2: RLM, Backbone=Mistral, Model Size=7B2026.03284.1