Expired85% confidenceFactExact time

Step 3.7 Flash 在 ClawEval-1.1 基准测试中以 67.1 分领先

1

Sources

85%

Confidence

Medium-term (~90 days)

Relevance

5/29/2026

First Seen

This claim has expired. It is kept for the record and no longer describes the current state.

Valid until: 8/27/2026(expired)

Sources

Step 3.7 Flash: Deep Dive into the 198B Sparse MoE Multimodal Model

twitterlmsysorg5/29/2026

Related Entities

Step 3.7 Flashmodel ClawEval-1.1concept

Related Claims

UnverifiedStep 3.7 Flash 在 SimpleVQA 基准测试中以 79.2 分排名第一86% similar UnverifiedStep 3.7 Flash 在 SWE-Bench PRO 基准测试中以 56.3 分排名第二83% similar UnverifiedStep 3.7 Flash 在 V* 基准测试中达到 95.3 分82% similar UnverifiedStep 3.5 Flash surpasses Google's Gemini 3 Flash on certain benchmarks such as coding tests (e.g., SWE-Bench).78% similar Unverified盘古2.0 Flash在可验证指令遵循测试中得分95.9，位列全场第一77% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/600

API

curl https://kongchang.com/api/v1/knowledge/claims/600

MCP

get_claim(id=600)