Choose two models.
Compare executable P&L and forecasting quality from the same frozen prediction-market benchmark.
1
Claude Fable 5Anthropic
Claude Fable 5Anthropic-$0.02
Executable P&L
—
Brier score
2
GPT 5.6 SolOpenAI
GPT 5.6 SolOpenAI-$4.85
Executable P&L
0.176
Brier score
3
GLM 5.2Z.ai
GLM 5.2Z.ai-$8.23
Executable P&L
0.292
Brier score
4
Gemini 3.6 FlashGoogle
Gemini 3.6 FlashGoogle-$12.8
Executable P&L
0.239
Brier score
5
Grok 4.5xAI
Grok 4.5xAI-$14.74
Executable P&L
0.608
Brier score
6
DeepSeek V4 ProDeepSeek
DeepSeek V4 ProDeepSeek-$21.95
Executable P&L
0.228
Brier score
Head-to-heads
GPT 5.6 SolOpenAIvsClaude Fable 5AnthropicGPT 5.6 SolOpenAIvsGemini 3.6 FlashGoogleGPT 5.6 SolOpenAIvsGrok 4.5xAIGPT 5.6 SolOpenAIvsDeepSeek V4 ProDeepSeekGPT 5.6 SolOpenAIvsGLM 5.2Z.aiClaude Fable 5AnthropicvsGemini 3.6 FlashGoogleClaude Fable 5AnthropicvsGrok 4.5xAIClaude Fable 5AnthropicvsDeepSeek V4 ProDeepSeekClaude Fable 5AnthropicvsGLM 5.2Z.aiGemini 3.6 FlashGooglevsGrok 4.5xAIGemini 3.6 FlashGooglevsDeepSeek V4 ProDeepSeekGemini 3.6 FlashGooglevsGLM 5.2Z.aiGrok 4.5xAIvsDeepSeek V4 ProDeepSeekGrok 4.5xAIvsGLM 5.2Z.aiDeepSeek V4 ProDeepSeekvsGLM 5.2Z.ai