BREAKING
Grok 4.5 Tops Non-Anthropic Models
0
Elo
AA-Briefcase
0
Intelligence Index
0
%
Rubric pass rate
AA-Briefcase Elo Ranking
Fable 5
1390
Opus 4.8
1354
Grok 4.5
1328
GDPVal+ Mean Pass Rate
Grok 4.5
29
GPT-5.5
22
Opus 4.8
21
Strengths vs Tradeoffs
Strengths
●
Fast, low-cost, token-efficient
●
Strong agentic workflows in Cursor
●
$2 in / $6 out per 1M tokens
Tradeoffs
●
Trails top Claude on presentation
●
Hallucination at 54%
●
Not yet offered in the EU
xAI Bets on Cost and Efficiency
AI NEWS BLITZ
Grok 4.5 from SpaceXAI ranks as the top non-Anthropic model on the AA-Briefcase benchmark.