EdTech Tracker

← Coding lens

sonnet

tool judged 0% likely a named technique or architecture

First seen
2024-06-26
Independent sources
17
Articles
57
Last 4 weeks vs prior
0 vs 20

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
09182024-W262026-W112026-W41
Table view
WeekArticlesSources
2024-W2611
2024-W3311
2024-W4711
2025-W0811
2025-W1011
2025-W1122
2025-W2211
2025-W3611
2025-W3911
2026-W0222
2026-W0311
2026-W0711
2026-W0921
2026-W1181
2026-W1211
2026-W2411
2026-W2522
2026-W2711
2026-W2811
2026-W2911
2026-W3211
2026-W3511
2026-W3611
2026-W3722
2026-W3811
2026-W40186
2026-W4121

In their words

dataframe ( failures [[ ' test_case_id ' , ' input ' , ' model_output ' , ' scores ' ]]) Model Comparison Framework # compare_models.py from concurrent.futures import ThreadPoolExecutor MODELS = [ ( " gpt-4o " , " openai " ), ( " gpt-4o-mini " , " openai " ), ( " claude-3.5-sonnet " , " anthropic " ), ( " llama-3.1-70b " , " together " ), ( " llama-3.1-8b " , " together " ), ] def evaluate_model (

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).

The Intelligence Layer: A frontier model (GPT-4o or Claude 3.5 Sonnet) providing the reasoning engine.

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

Dynamic Model Fallback Execution Pattern If the primary model endpoint (e.g., Claude 3.5 Sonnet) exceeds a latency budget or throws a transient HTTP error, the pipeline immediately reroutes the execution to a secondary provider or smaller, faster model tier (e.g., GPT-4o-mini or Llama 3) without failing the client request.

Routine work: Sonnet primary , with an Opus oracle for hard decisions.

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