Unverified50% confidenceBenchmarkExact time
According to the paper's data, on the CVDP benchmark, RTL-Interact-32B achieves 48.7% weighted Pass@1 and 68.9% Pass@5, surpassing its teacher model DeepSeek-V3.2.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedA 360M-parameter code model trained by the trifero.ai lab under Strife Technologies initially reported 26.8% pass@1 on HumanEval, and after removing instruction data overlapping with the benchmark, the true number was 22.6%.60% similarUnverifiedDeReAct improves the Pass@1 of Qwen3-Coder-480B by 6.5 to 7.0 percentage points.60% similarUnverifiedOn T180, TCSP3.0's Top-1 match rate (72.2%) outperforms PNcsp+ and the deep generative models CrystalFlow and MaskGXT (at most 63.9%).57% similarUnverifiedOn the Aider Polyglot coding test, DeepSeek at full precision scored 71.6%, Unsloth's 4-bit dynamic version scored 69.7%, the 2-bit version scored 65.8%, while a competing quantization solution of the same 2-bit depth and file size scored only 56.6%.57% similarUnverifiedIn a needle-in-a-haystack experiment with a 128K Token context and about 16,000 key-value pairs, changing the position of just one key-value pair produced a maximum accuracy gap of 40.2% for DeepSeek-V4-Flash-Base, 34.8% for DeepSeek-V4-Pro-Base, and still 19.1% and 14.8% respectively after post-training optimization.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125235API
curl https://kongchang.com/api/v1/knowledge/claims/1125235MCP
get_claim(id=1125235)