[KongchangAI]
Unverified50% confidenceFactExact time

The small model GLM5 paired with an evolved harness beat the stronger model Gemini 3.5 Flash running the default harness, and when the harness evolved for Gemini was handed unchanged to the small model, the latter's coding score immediately jumped by 17 points.

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/24/2026
First Seen
Valid until: 1/22/2027

Sources

Harness² Explained: Letting Agents Evolve Their Own Harness Without Training Models

Related Entities

GLM5modelGemini 3.5 Flashmodel

Related Claims

UnverifiedAccording to a content creator's hands-on testing, GLM-5.3 Flash scored close to Claude Opus 4.8 on the Terminal Bench 2.1 complex terminal task test.75% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/1093663
API
curl https://kongchang.com/api/v1/knowledge/claims/1093663
MCP
get_claim(id=1093663)