Unverified50% confidenceBenchmarkExact time
Fable 5.1在KingBench 3小型测试中获得74/80（92.5%），比Astra高2分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedFable 5在SWE Bench Pro编程测试上得分80.3分，而OpenAI的GPT 5.5仅为58.6分71% similarUnverifiedClaude Fable 5.1 在 CursiveBench 3.2.0 得分达到73.4，并在 OS World 2.0 等基准全面超越前代70% similarUnverified在Terminal Bench 2.1上Sol Ultra模式接近92%，超过Mythos 5的88%65% similarUnverified在SWE-Bench Multilingual测试中，HY3得分75.8，略微落后于DeepSeek V4 Pro的76.263% similarUnverifiedFable 5.1 在 Terminal Bench Science 0.1 基准测试中得分 52.6%，相比上一代翻了一倍多63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/897210API
curl https://kongchang.com/api/v1/knowledge/claims/897210MCP
get_claim(id=897210)