Unverified50% confidenceBenchmarkExact time
For Claude Opus 5.5, GPT-5.5 and Gemini 3.6 Flash (low reasoning effort), the shortcut gap reaches as high as +18 to +37 percentage points.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/18/2026
First Seen
Valid until: 12/2/2026
Sources
Related Entities
Related Claims
UnverifiedOn the Frontier Code programming benchmark, the old model scored 34.4%, while Gemini 3.7 Flash improved to 43.6%.74% similarUnverifiedAcross nine revised runs, the median completion speedup was 5.35× for Gemini, 3.69× for Claude, and 1.00× for GPT-5.4, with all three passing automated checks.74% similarUnverifiedFabrication rates when the total is fully obscured: Claude Sonnet 5 at 38%, Gemini 3 Flash at 21%, Gemini 3.1 Flash-Lite at 44%, GPT-5.4 nano at 73%; fabrication rates when the total is half-obscured: Claude at 92%, the other three models all at 100%.73% similarUnverifiedOpus 5.5 is less token-efficient than Opus 5: Opus 5's max tier uses 73k tokens per task, Fable uses 78k, Opus 5.5's max tier approaches 120k tokens, while GPT-6 Astra only requires 27k.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182628API
curl https://kongchang.com/api/v1/knowledge/claims/1182628MCP
get_claim(id=1182628)