List your company

Betting on Prediction Markets (test)

0.0838Delta SQwen 3 235B
-0.002520.019890.04230.06471Jul 7, 2026

Evaluation results

MethodLinks
Qwen 3 235B2026.070.0838-13.3-5.3-14.812.2-9.3-99.9
DeepSeek R12026.070.0636-20.3-7.6-25.40.7-9.6-99.9
Minimax M22026.070.05371.3-4-22.8-6.5-3.9-99.9
Kimi K2 Thinking2026.070.0492-9.5-3.1-24.31.5-2.5-99.9
DeepSeek V3.22026.070.0466-12.2-7.3-30.2-5.1-5.8-99.9
Grok 4.1 Fast2026.070.0462-11.6-7.8-26.4-7-6.3-99.9
GPT-5.2 (High)2026.070.046-2.4-1.6-13.3-1.9-1-99.9
LLaMA 4 Maverick2026.070.045-13.7-4.1-15.5-4-10-99.9
Claude Sonnet 4.52026.070.0426-3.51.2-19.81.40.7-99.9
GPT-5.2 (Base)2026.070.03474.52.4-14.91.9-0.1-99.9
Claude Opus 4.62026.070.001622.15-14-3.510.9-99.9
Gemini 32026.070.00088.11.3-0.10.71.8-42.7