Unverified50% confidenceBenchmarkExact time
On the Qwen3.5-4B and 9B models, using only GGA allocation without any other changes improved the scores on seven evaluations by 19.48 and 29.84 percentage points, respectively, compared with STEPQuant@4.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedGlimmer's intelligence index score of 35 surpasses Gemma 2 27B (30) and nearly matches Qwen 2.5 (36), with Qwen 2.5 72B topping the leaderboard at 38.74% similarUnverifiedIn the GEPA paper, the merge operator can improve the average performance of gpt-4.1-mini but reduces the effectiveness of Qwen3-8B, an asymmetry that previously lacked explanation.73% similarUnverifiedQwen2.5-1.5B scores 0.729 on GSM8K, 18.2 percentage points lower than Gemma 4 E2B; Qwen3-0.6B scores 0.599, 31.2 percentage points lower; SmolLM2-1.7B scores 0.461, 45.0 percentage points lower.71% similarUnverifiedThe label-image accuracy gaps of GPT-4o, Qwen-VL Max, and LLaMA reach 9.5, 13.8, and 12.6 percentage points respectively.71% similarUnverifiedOn the Artificial Analysis benchmark, Qwen 3.8 approaches or even surpasses larger models such as GLM 5.2 Max, Kimi K3, and GPT 5.6.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114523API
curl https://kongchang.com/api/v1/knowledge/claims/1114523MCP
get_claim(id=1114523)