List your company

Task Performance on Search-R1

75.8Success RateClaude Opus 4.7
33.57644.53855.566.462May 29, 2026

Evaluation results

MethodLinks
Claude Opus 4.72026.0575.81.78
Claude Sonnet 4.62026.0571.11.87
GPT-5.2 Instant2026.05683.69
Gemini 3.1 Pro Preview2026.0553.92.09
Qwen3 235B2026.0535.29.94