Unverified50% confidenceBenchmarkExact time
On the Simple Bench commonsense reasoning test, Fable 5.2 scores about 95%, Gemini 4 Carbon 92.6%, and other models 91.7%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/11/2026
First Seen
Valid until: 2/9/2027
Sources
Related Entities
Related Claims
UnverifiedOn the Graphworks long-horizon reasoning benchmark, Gemini 4 Carbon scored 96.2%, higher than Argon's 84.2%.77% similarUnverifiedGemini 4 Carbon achieved 96.2% accuracy in finding clues within ultra-long texts of 250,000 to one million tokens.77% similarUnverifiedThird-party testing shows that the proportion of Gemini 4 Carbon forcibly fabricating answers to questions it cannot answer rose from 4% to 11%.75% similarUnverifiedOn Semi Analysis's GDPX benchmark, Fable 5.2 scores 16.4% and Gemini 4 Carbon scores 10.9%, but Gemini 4 Carbon's cost may be only one-fifth that of Fable 5.2; GPT-6 Astra scores lower and costs more.74% similarUnverifiedIn the Exploit Gym test, Gemini 4 Carbon's success rate in verifying vulnerability exploitability was 54.8%.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1157852API
curl https://kongchang.com/api/v1/knowledge/claims/1157852MCP
get_claim(id=1157852)