General Assistant Tasks on GAIA L1
69.5AccuracyExComm
Evaluation Results
| Method | Links | |
|---|---|---|
| ExCommBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.05 | 69.5 | |
| Independent ScalingBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.05 | 61.7 | |
| Independent Scaling + SRBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.05 | 60.8 | |
| Tree SearchBackbone=Qwen2.5-7B, N > 1?=true, Available Tools=C / F / S2026.05 | 58.7 | |
| Sequential Revision (SR)Backbone=Qwen2.5-7B, N > 1?=false, Available Tools=C / F / S2026.05 | 54 | |
| Base AgentBackbone=Qwen2.5-7B, N > 1?=false, Available Tools=C / F / S2026.05 | 53.7 | |
| ExCommBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.05 | 52.2 | |
| Independent ScalingBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.05 | 44 | |
| Independent Scaling + SRBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.05 | 42.7 | |
| Tree SearchBackbone=Gemini-2.5-Flash-Lite, N > 1?=true, Available Tools=C / F / S2026.05 | 41 | |
| Base AgentBackbone=Gemini-2.5-Flash-Lite, N > 1?=false, Available Tools=C / F / S2026.05 | 35.8 | |
| Sequential Revision (SR)Backbone=Gemini-2.5-Flash-Lite, N > 1?=false, Available Tools=C / F / S2026.05 | 35.2 |