Unverified50% confidenceBenchmarkExact time
The same harness scored 69.3 under one model but only 33.0 under another, indicating an extremely severe dependence on the executor.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe same model (with identical weights) scores 62% in one agent harness, but only 33% in a different harness, a gap of nearly 30 percentage points.72% similarUnverifiedThe same model paired with different harnesses can differ severalfold in actual performance.70% similarUnverifiedThe same scaffold raised the weak model's execution quality from 0.88 to 2.0 (across four scoring dimensions), yet pushed the strong model toward overcautious shutdown (all four dimensions dropped).69% similarUnverifiedUnder the DeepSuite V1.1 benchmark, the same model's scores fluctuate from 69.8% to 74.2% across different harnesses.67% similarUnverified如果模型跑BF16训练但DCGM_FI_PROF_PIPE_TENSOR_ACTIVE指标长期低于30%，基本可以断定算力被严重浪费65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038301API
curl https://kongchang.com/api/v1/knowledge/claims/1038301MCP
get_claim(id=1038301)