Unverified50% confidenceBenchmarkExact time
Sol在Terminal Bench 2.1编程测试中获得9019分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026
Sources
GPT-5.6三模型同时发布：Sol、Terra、Luna定位与核心差异解析
bilibili不到九点o7/9/2026
Related Claims
Unverified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%73% similarUnverified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71% similarUnverifiedSol在Terminal-Bench 2.0上达到了新水平67% similarUnverifiedExploitBench测试中Sol约76%略逊于Fable 5的78%，但Sol仅消耗约12-13万Token而Fable 5用约35万Token66% similarUnverifiedNex N2 Pro官方基准测试数据：Terminal Bench得分75.3分，SWE Bench Pro得分58.8分，GDP EVOL接近1600分62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488323API
curl https://kongchang.com/api/v1/knowledge/claims/488323MCP
get_claim(id=488323)