List your company

Web Agent Task Completion on GAIA

70.9AccuracySlimSearcher (SFT+RL)
32.4242.4152.462.39Jun 5, 2026

Evaluation results

MethodLinks
SlimSearcher (SFT+RL)Backbone Policy=Tongyi-DeepResearch, Optimization Strategy=SFT+RL2026.0670.910.614,915
WebLeaperType=Open-weights Agent2026.0670.216.655,045
SlimSearcher (SFT+RL)Backbone Policy=Qwen3-30B-A3B-Instruct-2507, Optimization Strategy=SFT+RL2026.0669.920.137,237
Claude-4-SonnetType=Proprietary System2026.0668.3——
Tongyi-DeepResearch2026.0668.220.567,378
OpenAI DeepResearchType=Proprietary System2026.0667.4——
SlimSearcher (SFT)Backbone Policy=Qwen3-30B-A3B-Instruct-2507, Optimization Strategy=SFT2026.0666.524.467,299
Prompt ControlBackbone Policy=Tongyi-DeepResearch, Optimization Strategy=Prompt Control2026.0666.318.76,752
SlimSearcher (SFT)Backbone Policy=Tongyi-DeepResearch, Optimization Strategy=SFT2026.066621.796,412
Kimi-K2-Instruct-0905Type=Open-weights Agent2026.0646.96.451,281
Qwen3-235B-A22B-InstructType=Open-weights Agent2026.0645.67.141,128
DeepSeek-V3Type=Open-weights Agent2026.0637.33.2994
WebExplorerType=Open-weights Agent2026.0637.212.883,560
Qwen3-30B-A3B-Instruct-2507Type=Open-weights Agent, Unified Environment=true2026.0633.911.63986