Unverified50% confidenceBenchmarkExact time
在Terminal Bench 2.1上Sol Ultra模式接近92%，超过Mythos 5的88%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026
Sources
GPT-5.6 Sol对决Fable 5：半价能否媲美旗舰？
bilibiliYoutube力工7/6/2026
Related Claims
Unverified在Terminal Bench 2.1基准测试上，GPT-5.6 Sol的Ultra模式接近92%，超越竞品的88%表现73% similarUnverified在Exploit Bench网络安全基准上，Sol得分约76%，Mythos 5约78%73% similarUnverified普通版 Sol 在 Terminal Bench 2.1 基准测试中获得 88.8%，开启 Ultra 模式后提升至 91.9%68% similarUnverified在Artificial Analysis的Omniscience幻觉指标上，GPT-5.6 Sol Max高达89%，高于Claude Fable的55%和GLM 5.2的28%67% similarUnverified在SWE-Bench Pro编程评测上，Claude Fable 5以80%的成绩领先GPT-5.6 Sol的64.6%64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/249746API
curl https://kongchang.com/api/v1/knowledge/claims/249746MCP
get_claim(id=249746)