Unverified50% confidenceBenchmarkExact time
In a test with regular tabular data of 10 rows and 4 fields per row, encoded using the cl100k_base tokenizer, JSON was 323 tokens and 963 characters, while YAML was 221 tokens and 590 characters, with YAML ahead by 31.6%; the TOON format was 97 tokens and 235 characters, 70% fewer than JSON and 56.1% fewer than YAML.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQwen3 27B natively supports a context of 262,000 tokens and can be extended to 1,000,000 tokens via YaRN extrapolation.60% similarUnverifiedThe Chinchilla model, with 70B parameters and 1.4T tokens, significantly outperforms the Gopher model, which has 280B parameters and 300B tokens, under the same compute budget.59% similarUnverifiedThe author reproduced it on a T4 with the same model and testing method: at 8 concurrency, a single request decodes at 122–124 tokens/s, and the whole server produces 701–708 tokens/s, likewise about a 5.7-fold difference.58% similarUnverifiedIn a pydantic-ai test, after 10 parallel tool calls (21 new blocks), the next request read 6,827 tokens from cache; after 11 calls (23 blocks), the read count was 0 and 7,534 tokens were written again.58% similarUnverifiedRegardless of the encoding scheme used, 4-bit precision can only distinguish 16 different numerical levels.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016891API
curl https://kongchang.com/api/v1/knowledge/claims/1016891MCP
get_claim(id=1016891)