List your company

General Deep Research Tool Use on BrowseComp

49Success RateGemini-3-Pro
-0.60812.27125.1538.029Mar 10, 2026

Evaluation results

MethodLinks
Gemini-3-ProCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0349
DeepSeek-V3.2-ExpCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0340.1
GPT-OSS-120BCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0327
DIVE-8B (RL)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.0316.4
WebExplorer-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.0315.7
Kimi-K2-0905Category=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0314.1
DIVE-8B (SFT)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.0312.9
Claude-4-SonnetCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0312.8
Gemini-2.5-ProCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.039.9
EnvScaler-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.031.7
SWE-Dev-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.031.6
Qwen3-8B (base)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.031.3