Unverified50% confidenceBenchmarkExact time
Zero-shot Gemma 3 270M is nearly unusable on the grammar correction task, with an F0.5 of only 0.122, and 99.6% of correct sentences were altered.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedGemma 4 26B terminated with a runtime error before producing a score, because the scoring code assumed at least one sentence would be returned in the correct structured format.71% similarUnverifiedWhen Gemma wrote entire messages directly, it dropped all numbers in 4 out of 4 tests and completely reversed the meaning twice.66% similarUnverifiedAfter re-evaluation, Gemma 12B in non-thinking mode achieved a substantive pass rate of 12/16, while the strict pass rate remained at 4/16.64% similarUnverifiedThe Gemma 4 31B version, while maintaining a relatively small parameter count, attempts to strike a balance between conversational quality and breadth of knowledge.61% similarUnverifiedGemma's parameter scale ranges from 2B to 27B.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009451API
curl https://kongchang.com/api/v1/knowledge/claims/1009451MCP
get_claim(id=1009451)