Expired50% confidenceBenchmarkExact time
In the Frontier Code accuracy vs. cost benchmark, the low tier costs approximately $5 to achieve around 11% score, while Opus 4.8 Max costs approximately $11 to achieve the same score.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/20/2026(expired)
Sources
Related Claims
UnverifiedClaude Opus 5 approaches Fable-level performance on the FrontierCode 1.1 benchmark while costing only half as much76% similarUnverifiedOpus 5's pass rate at Low Effort is approximately 60%, surpassing Opus 4.8's 59% at the Max level, for which the per-task cost is as high as $13.72% similarUnverifiedUnder medium reasoning intensity in the ELE test, Sol's cost is approximately 1/4 that of Faber-5, while Terra and Luna cost only about 1/16 and still score above Faber-5.69% similarVerifiedClaude Opus 4.8的输入/输出token比价为1:563% similarUnverifiedBy introducing verification loops as an engineered reasoning framework, the actual intelligence performance of DeepSeek can be improved approximately 4x, at a cost of only one-seventh that of Claude Opus.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593987API
curl https://kongchang.com/api/v1/knowledge/claims/593987MCP
get_claim(id=593987)