Unverified50% confidenceBenchmarkExact time
GAD-RL achieved an Overall total score of 91.18 on OmniDocBench v1.6
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/1/2026
First Seen
Valid until: 12/30/2026
Sources
Related Entities
Related Claims
UnverifiedOn the Qwen3.5-2B model, GAD-RL achieved a Micro Recall of 59.92% on CHAOS-Bench, surpassing GRPO and fixed-weight GRPO+OPD by 8.45 and 4.43 percentage points respectively66% similarUnverifiedOn the MCP Atlas benchmark, Glimmer scored 75.5, Gemma 4 scored 54.2, and Qwen 3.6 scored 62.5.58% similarUnverifiedOn the Rule Induction task, TwIL-LM3 scored 96.4 while gpt-oss-120b scored 65.2.57% similarUnverifiedGrok 4.7 achieved 71.0% on the Deep SWE software engineering evaluation, 38.0% on TerminalBench, and an Elo of 1,695 on the GDPVal evaluation, second only to Fable 5.1's 1,735.57% similarUnverifiedThe best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963915API
curl https://kongchang.com/api/v1/knowledge/claims/963915MCP
get_claim(id=963915)