List your company
ResearchFormerly WizWand

General AI Assistant Task on GAIA-127 (Accuracy)

23.6AccuracyOpenThinkerAgent-32B
4.2569.27814.319.322Jun 23, 2026
Updated 4mo ago

Evaluation results

MethodLinks
OpenThinkerAgent-32BTrain Size=100K, Method=SFT, Backbone=Qwen3-32B2026.0623.6
Nemotron-Terminal-32BTrain Size=264K, Method=SFT, Backbone=Qwen3-32B2026.0622.3
DeepSWE-PreviewTrain Size=4.5K, Method=RL, Backbone=Qwen3-32B2026.0616.5
Nemotron-Terminal-8BTrain Size=264K, Training Method=SFT2026.0614.4
SWE-Lego-Qwen3-32BTrain Size=18K, Method=SFT, Backbone=Qwen3-32B2026.0612.9
SA-SWE-32BTrain Size=4.5K, Method=RL, Backbone=Qwen3-32B2026.0611.5
Qwen3-32BTrain Size=N/A, Method=N/A, Backbone=Qwen3-32B2026.069.7
SERA-32BTrain Size=25K, Method=SFT, Backbone=Qwen3-32B2026.068.7
OT-Agent-ColdSFT+RL-8BBase Model=OpenThinker-Agent-v1-SFT, Train Size=10K+5K, Training Method=SFT+RL2026.066.8
OT-Agent-SFT-8B (100K)Base Model=OpenThinker-Agent-v1-SFT, Train Size=100K, Training Method=SFT2026.066.6
SWE-Lego-Qwen3-8BBase Model=Qwen3-8B, Train Size=18K, Training Method=SFT2026.066
OT-Agent-SFT-8B (10K)Base Model=OpenThinker-Agent-v1-SFT, Train Size=10K, Training Method=SFT2026.065.5
Endless TerminalsBase Model=Qwen3-8B, Train Size=15K+3K, Training Method=SFT+RL2026.065.2
Qwen3-8BBase Model=N/A, Train Size=N/A, Training Method=N/A2026.065