Expired50% confidenceBenchmarkExact time
On Exploit Bench, Sol can compete with Anthropic models while using approximately one-third of the output tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/10/2026
First Seen
Valid until: 10/8/2026(expired)
Sources
GPT-5.6 Three-Model Benchmark: How Close Are Sol/Terra/Luna to Claude?
bilibili烟神殿副殿主7/9/2026
Related Claims
UnverifiedSol's output token count and completion time are both less than half of competitors', with an estimated cost approximately one-third lower.73% similarUnverified在编程智能体测试中，Sol 输出的 Token 少了一半以上，成本约为 Faber-5 的 1/369% similarUnverifiedOn the Artificial Analysis coding agent index, Sol set to the highest reasoning tier scored 80, surpassing Fable 5 by 2.8 points, while using less than half the output tokens, taking less than half the time, and costing roughly one-third less.67% similarUnverifiedOn SimpleBench, Sol Pro scored 71.7% and Sol approximately 65%, still 10 percentage points below Fable.64% similarUnverifiedLuna作为轻量模型，其参数规模和推理计算量显著低于Sol，单次调用成本可能仅为Sol的几分之一60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/452864API
curl https://kongchang.com/api/v1/knowledge/claims/452864MCP
get_claim(id=452864)