EdTech Tracker

← Coding lens

claude sonnet

tool judged 0% likely a named technique or architecture

First seen
2024-11-18
Independent sources
13
Articles
31
Last 4 weeks vs prior
0 vs 11

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
05102024-W472026-W122026-W41
Table view
WeekArticlesSources
2024-W4711
2025-W1011
2025-W2211
2025-W3911
2026-W0211
2026-W0311
2026-W0711
2026-W0911
2026-W1131
2026-W1211
2026-W2411
2026-W2711
2026-W2811
2026-W2911
2026-W3611
2026-W3722
2026-W3811
2026-W40105
2026-W4111

In their words

Sources and disclosure The lookback numbers are my own measurement: two requests per size on Amazon Bedrock, Claude Sonnet 4.6, us-west-2, October 2026, run twice each with fresh prompts so an old cache entry could not fake a hit ( scripts/live_lookback_boundary.py in the CacheCanary repo).

Model Cost per task (USD) Pass rate Tasks run gpt-6-luna 0.0010 92 % 12 gemini-3.1-flash-lite 0.0012 67 % 12 claude-haiku-5-5 0.0023 75 % 12 gemini-3.5-flash-lite 0.0028 83 % 12 deepseek-flash 0.0051 88 % 8 deepseek-v4-pro 0.0097 100 % 2 qwen3.8-max 0.0137 100 % 1 glm-5.3 0.0198 67 % 6 claude-sonnet-5-5 0.0306 83 % 12 claude-opus-5-5 0.0799 92 % 12 Rows with fewer than 12 tasks are partial runs; d

TL;DR Same RAG pipeline, two setups: a MacBook Air running a local 4B model, and Claude Sonnet 5.5.

Architecture Browser Server (Java / Spring) ─────── ────────────────────── Stockfish WASM (Web Worker) Pool of native Stockfish (3 processes) ├─ coach's own moves (MultiPV 6) ├─ game review (depth 14, recheck at 18) └─ judging the player's move (depth 12) └─ answering questions (depth 14, top 3 moves) │ facts (JSON) Question (text / voice) ─────────────► Claude Sonnet 5 + "analyze" tool │ text Ans

Similar questions came up last month when Anthropic said it could route Claude Sonnet 5.5 requests to Sonnet 5 when it detects higher-risk activity.

Anthropic, aynı değerlendirmeleri Claude Sonnet 5.5 üzerinde de çalıştırıp karşılaştırmanızı önerir.

De 1 a 24/09/2026, o Claude Sonnet 5 teve 1,83 milhão de tokens escritos no cache de prompt e zero lidos, porque a validade de 5 minutos acabava entre uma chamada Anthropic e a seguinte.

get_encoding ( " cl100k_base " ) MODEL = " claude-sonnet-5-5 " TARGET = 194_000 # real tokens; headroom under the 200K window FAST_RATIO = 1.2 # pessimistic tiktoken multiplier for the first pass def real_count ( system , messages , tools ): resp = client .