List your company
ResearchFormerly WizWand

General Assistant Tasks on GAIA L3

28.7AccuracyExComm
3.94810.37416.823.226May 21, 2026
Updated 5mo ago

Evaluation results

MethodLinks
ExCommBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.0528.7
Independent Scaling + SRBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.0526.5
Sequential Revision (SR)Backbone=Qwen2.5-7B, N > 1?=false, Available Tools=C / F / S2026.0521
Independent ScalingBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.0520.1
Tree SearchBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.0516.7
Base AgentBackbone=Qwen2.5-7B, N > 1?=false, Available Tools=C / F / S2026.0516.4
ExCommBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.0514.8
Tree SearchBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.0510.2
Independent ScalingBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.059
Base AgentBackbone=Gemini-2.5-Flash-Lite, N > 1?=false, Available Tools=C / F / S2026.055.9
Independent Scaling + SRBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.055.6
Sequential Revision (SR)Backbone=Gemini-2.5-Flash-Lite, N > 1?=false, Available Tools=C / F / S2026.054.9