Unverified50% confidenceBenchmarkExact time
When completing the same tasks, SWE-2 requires 58% fewer interaction turns than its predecessor SWE-1.7, costs 81% less, and achieves a higher score.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/13/2026
First Seen
Valid until: 12/12/2026
Sources
Related Entities
Related Claims
UnverifiedOn the AppWorld benchmark, SMC reduces actual runtime by 7.7% compared to the SA baseline and by 44.9% compared to serial execution, with only a slight decrease in task completion rate.68% similarUnverifiedThe per-task cost of GPT-6 Astra is lower than that of its predecessor, because a more capable model completes the same task in fewer steps and with fewer tokens.64% similarUnverifiedCombining multiple optimization techniques, some vendors have reduced inference costs by more than 80% compared to two years ago.63% similarUnverified代码执行方案将相同任务的token消耗从15万降至2000，减少了98.7%63% similarUnverifiedThe marginal cost of AI models decreases as scale expands; the more users there are, the lower the average cost per inference after optimization through batching and GPU utilization.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/918913API
curl https://kongchang.com/api/v1/knowledge/claims/918913MCP
get_claim(id=918913)