Unverified50% confidenceBenchmarkExact time
On τ²-Bench, SpecAgent's success rate is within less than one percentage point of the strong model, while memory traffic and wall-clock time are roughly halved.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFastEmbed-rs所使用的量化模型在MTEB基准测试中相比全精度模型的性能下降通常控制在1-2%以内70% similarUnverifiedAt epoch 290, the loss rebounded (+0.002), indicating that the model may have approached the performance ceiling of its current configuration.70% similarUnverifiedThe small model pair halves the download size and reduces peak memory by about 35% compared with the original model pair, but in this trial the full turn was actually slower.69% similarUnverifiedThe 406M model's peak inference memory is less than half that of the 1.2B system, its parameter count is approximately one-third, and the two are comparable in performance.68% similarUnverifiedCognition states that SWE-2 scores only one point below Anthropic's Claude model on its own coding benchmarks, yet costs 64% less68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046817API
curl https://kongchang.com/api/v1/knowledge/claims/1046817MCP
get_claim(id=1046817)