Model vs Model — All Comparisons

Compare any two AI models on their FIFA World Cup 2026 match predictions. 12 models · 66 pairings · sorted by most disagreements.

PairingDisagreementsAgreements
Gemini 3.1 Pro vs Mistral Large 33240
Kimi K2.6 vs Mistral Large 33141
Claude Opus 4.8 vs Mistral Large 33042
Gemini 3.5 Flash vs Mistral Large 33042
GPT-5.5 High vs Mistral Large 32943
MiMo v2.5-Pro vs Mistral Large 32943
DeepSeek V4 Pro vs Mistral Large 32844
GLM-5.1 vs Mistral Large 32844
Grok 4.3 vs Mistral Large 32745
Claude Sonnet 4.6 vs Mistral Large 32448
Claude Opus 4.8 vs Claude Sonnet 4.62349
Gemma 4 31B vs Mistral Large 32349
Claude Sonnet 4.6 vs Gemma 4 31B2052
Claude Sonnet 4.6 vs Grok 4.31953
Claude Opus 4.8 vs Gemini 3.1 Pro1854
Claude Opus 4.8 vs Gemma 4 31B1854
Claude Sonnet 4.6 vs Gemini 3.1 Pro1854
Claude Sonnet 4.6 vs Gemini 3.5 Flash1854
Claude Sonnet 4.6 vs MiMo v2.5-Pro1854
Claude Opus 4.8 vs Kimi K2.61755
Claude Sonnet 4.6 vs Kimi K2.61755
Gemma 4 31B vs Grok 4.31755
Claude Sonnet 4.6 vs GPT-5.5 High1656
Claude Sonnet 4.6 vs GLM-5.11656
Claude Sonnet 4.6 vs DeepSeek V4 Pro1557
Gemini 3.1 Pro vs Gemma 4 31B1557
GPT-5.5 High vs Grok 4.31557
Grok 4.3 vs MiMo v2.5-Pro1557
Claude Opus 4.8 vs Gemini 3.5 Flash1458
Claude Opus 4.8 vs Grok 4.31458
Gemini 3.1 Pro vs MiMo v2.5-Pro1458
Grok 4.3 vs Kimi K2.61458
DeepSeek V4 Pro vs Gemma 4 31B1458
Gemma 4 31B vs MiMo v2.5-Pro1458
Claude Opus 4.8 vs DeepSeek V4 Pro1359
DeepSeek V4 Pro vs Gemini 3.1 Pro1359
Gemma 4 31B vs GPT-5.5 High1359
Gemma 4 31B vs GLM-5.11359
Gemma 4 31B vs Kimi K2.61359
Claude Opus 4.8 vs GPT-5.5 High1260
Gemini 3.1 Pro vs Grok 4.31260
Gemini 3.1 Pro vs GLM-5.11260
Gemini 3.1 Pro vs Kimi K2.61260
Gemini 3.5 Flash vs Grok 4.31260
Gemini 3.5 Flash vs MiMo v2.5-Pro1260
Gemini 3.5 Flash vs Gemma 4 31B1260
Kimi K2.6 vs MiMo v2.5-Pro1260
Claude Opus 4.8 vs GLM-5.11161
Claude Opus 4.8 vs MiMo v2.5-Pro1161
Gemini 3.1 Pro vs GPT-5.5 High1161
DeepSeek V4 Pro vs Gemini 3.5 Flash1161
DeepSeek V4 Pro vs Grok 4.31161
GLM-5.1 vs Grok 4.31161
DeepSeek V4 Pro vs MiMo v2.5-Pro1161
DeepSeek V4 Pro vs Kimi K2.61161
Gemini 3.1 Pro vs Gemini 3.5 Flash1062
Gemini 3.5 Flash vs GPT-5.5 High1062
Gemini 3.5 Flash vs GLM-5.11062
Gemini 3.5 Flash vs Kimi K2.61062
GPT-5.5 High vs MiMo v2.5-Pro1062
GPT-5.5 High vs Kimi K2.61062
GLM-5.1 vs MiMo v2.5-Pro1062
DeepSeek V4 Pro vs GPT-5.5 High864
GLM-5.1 vs GPT-5.5 High864
GLM-5.1 vs Kimi K2.6864
DeepSeek V4 Pro vs GLM-5.1765