List your company

General Deep Research Tool Use on HLE

42.9Success RateGemini-3-Pro
1.19612.02322.8533.677Mar 10, 2026

Evaluation results

MethodLinks
Gemini-3-ProCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0342.9
Gemini-2.5-ProCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0328.4
Kimi-K2-0905Category=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0326.9
Claude-4-SonnetCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0320.8
GPT-OSS-120BCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0319
DeepSeek-V3.2-ExpCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0317.9
DIVE-8B (RL)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.0317.8
WebExplorer-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.0317.3
DIVE-8B (SFT)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.0313.8
SWE-Dev-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.036.9
Qwen3-8B (base)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.036.4
EnvScaler-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.032.8