Expired50% confidenceBenchmarkExact time
Sol reached a new level on Terminal-Bench 2.0.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
Valid until: 10/7/2026(expired)
Sources
GPT-5.6 Explained: Sol, Terra & Luna — Tiered Positioning and Capability Comparison
bilibiliX信息差6/28/2026
Related Claims
UnverifiedSol scored 9019 points on the Terminal Bench 2.1 programming benchmark.67% similarUnverifiedThe standard version of Sol scored 88.8% on the Terminal Bench 2.1 benchmark, which improved to 91.9% with Ultra mode enabled.60% similarUnverifiedThe Sol configuration answered all of the first 6 out of 10 runs correctly in HIGH mode, and maintained a perfect score across multiple runs in XH mode.54% similarUnverifiedSol 在编程智能体指数全推理模式下拿到 80 分，刷新 SOTA，比 Faber-5 高 2.8 分53% similarUnverifiedIn full-fidelity prototype comparisons, Sol won three to four out of five times.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/389030API
curl https://kongchang.com/api/v1/knowledge/claims/389030MCP
get_claim(id=389030)