List your company

Reasoning over conflicting evidence on SEAL-0

45.9AccuracyROMA
2.84414.02225.236.378Feb 2, 2026

Evaluation results

MethodLinks
ROMASource type=Open-source, Search=true, backbone=GLM-4.62026.0245.9
Kimi-ResearcherSource type=Open-source, Search=true2026.0236
Perplexity Deep ResearchSource type=Closed-source, Search=true2026.0231.5
Grok-4Source type=Closed-source, Search=true2026.0220.7
Gemini 2.5 ProSource type=Closed-source, Search=true2026.0219.8
o3-proSource type=Closed-source, Search=true2026.0218.9
o3Source type=Closed-source, Search=true2026.0215.3
GLM-4.6Source type=Open-source, Search=true2026.0214.5
Gemini 2.5 FlashSource type=Closed-source, Search=true2026.0213.5
Perplexity Sonar Reasoning ProSource type=Closed-source, Search=true2026.0213.5
Open Deep SearchSource type=Open-source, Search=true, backbone=DeepSeek-R12026.029.9
Grok-3Source type=Closed-source, Search=true2026.025.4
Qwen3-235B-A22BSource type=Open-source, Search=true2026.025.4
DeepSeek-R1Source type=Open-source, Search=true2026.024.5