List your company

In-distribution Tool Use on DIVE-Eval

45.3Success RateGemini-3-Pro
11.70820.42929.1537.871Mar 10, 2026

Evaluation results

MethodLinks
Gemini-3-ProCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0345.3
Claude-4-SonnetCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0344.8
DIVE-8B (RL)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.0342.5
GPT-OSS-120BCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0340.5
DeepSeek-V3.2-ExpCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0340.4
DIVE-8B (SFT)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.0335.4
Kimi-K2-0905Category=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0332.9
Gemini-2.5-ProCategory=Frontier (≫8B), Temperature=1, Top-p=1, Number of runs=42026.0329.1
WebExplorer-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.0319.1
EnvScaler-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.0315.4
SWE-Dev-8BCategory=8B Baselines, Temperature=1, Top-p=1, Number of runs=42026.0313.8
Qwen3-8B (base)Category=Ours, Temperature=1, Top-p=1, Number of runs=42026.0313