Unverified50% confidenceBenchmarkExact time
SpatialOPSD retains about 91% of the performance of the teacher model SpatialClaw on Qwen3.5-9B (51.9 versus 57.3).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedOn the Qwen3-VL-4B model, fine-tuning with procedurally generated data raises its accuracy on SpaceCast-Bench from 34.0% to 65.7%, and achieves a macro-average gain across six out-of-domain benchmarks.62% similarUnverifiedMATE paired with the Qwen2.5-14B model achieves a task success rate of 81.3%.62% similarUnverifiedOn Qwen-3.5-4B-Instruct, 75.6% of validity scores judged that the generated results at both poles of the principal axes accurately corresponded to their labels, with an annotator adjacent-agreement rate as high as 90.9%.60% similarUnverified3,189 successful rollouts were collected from Qwen3.8-27B for supervised fine-tuning (imitation learning), and performance stagnated at 47.5%, below the results of two rounds of RL training.59% similarUnverifiedOn agentic coding benchmarks such as SWE Bench Pro, Qwen 3.8 reportedly surpasses Opus 4.6 Max on some tasks.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033276API
curl https://kongchang.com/api/v1/knowledge/claims/1033276MCP
get_claim(id=1033276)