Expired50% confidenceBenchmarkExact time
In the blogger's self-built GoldieBench evaluation, Agent A1 scored 4.8/10, ranking second, surpassing Gemma 4 but with a notable gap compared to the Qwen series (approximately 7.14 points).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026(expired)
Sources
Related Claims
UnverifiedIn a local inference speed comparison, Agent A1 (95 tokens/second) was faster than Gemma 4 Coder and the Qwen series.61% similarUnverifiedOmniMerge V4 scored 84.76 on the HumanEval test, on par with the Q6K original version.58% similarUnverifiedQwen 3.6 Plus received a composite score of 69.0, ranking last and being eliminated.57% similarUnverifiedOn the HLE science benchmark, Agent A1 surpassed Qwen 3.6 and Step 3.5 Flash according to actual test data.57% similarUnverified跑分排名不等于所有场景的实际表现，Terra跑分接近5.5但游戏任务中5.5完成度略高56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593885API
curl https://kongchang.com/api/v1/knowledge/claims/593885MCP
get_claim(id=593885)