Unverified50% confidenceBenchmarkExact time
Under one task ordering, the final held-out loss across four tasks decreased from 2.927 to 1.114; under the reverse task ordering, it decreased from 2.168 to 0.891.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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%70% similarUnverifiedThere were 100 tasks on which performance losses relative to the baseline persisted across all three repetitions, while persistent wins occurred on only 1 task.67% similarUnverifiedFor a task that sequentially calls 5 APIs, even if the success rate of each step is 95%, the overall success rate drops to approximately 77%.66% similarUnverified在 Terminal Bench 2.1 测试中，OpenCode 对比里 89 个任务的失败数从 29 降到 16，多解决 13 题，分数提升 14.61 个百分点64% similarUnverifiedFor two-step and three-step compositional tasks, the median paired difference in accuracy under the masking condition reaches 0.846 and 0.859, respectively.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/982976API
curl https://kongchang.com/api/v1/knowledge/claims/982976MCP
get_claim(id=982976)