Models

33 models so far, most recently run first. Each page has every task the model ran, with every check and what each run did.

• Opus 5.5last run 2026-11-09
  anthropic/claude-opus-5.5

  41 runs on French press, Portafilter, Venn, Bean cosy, Pruned shrub, Coffee tree, Verdict, good press, Verdict, flipped, Serve the tray, Four tables, three drinks, Two tables, black coffee and Pump noise

• GPT-6.1 Sollast run 2026-11-09
  openai/gpt-6.1-sol

  42 runs on French press, AeroPress, V60, Portafilter, Grinder, Bean cosy, Five circles, Triangle wave, Pruned shrub, Penrose floor, Espresso Rag, Serve the tray, Four tables, three drinks, Two tables, black coffee and Pump noise

• Gemini 4 Argonlast run 2026-11-09
  google/gemini-4-argon

  9 runs on Pruned shrub, Coffee tree and Pump noise

• Kimi K3.1 Prolast run 2026-11-09
  moonshotai/kimi-k3.1-pro

  26 runs on French press, AeroPress, Bean cosy, Pruned shrub, Hopper, Serve the tray, Four tables, three drinks, Two tables, black coffee and Pump noise

• GPT-6.1 Terralast run 2026-11-09
  openai/gpt-6.1-terra

  3 runs on Pump noise

• GLM 5.3 FlashXlast run 2026-11-08
  z-ai/glm-5.3-flashx

  44 runs on French press, Portafilter, COFFEE route, Venn, Bean cosy, Pruned shrub, Stirring spoon, V60 repair, Spoon repair, Venn repair, Knitting repair, Serve the tray, Four tables, three drinks and Two tables, black coffee

• DeepSeek 4.1 Flashlast run 2026-11-08
  deepseek/deepseek-v4.1-flash

  69 runs on French press, Portafilter, COFFEE route, Caffeine, Boiler, Café table, Fluorocaffeine, Venn, Bean cosy, Five circles, Triangle wave, Café order, Pruned shrub, Coffee tree, Hopper, Stirring spoon, V60 repair, Spoon repair, Venn repair, Knitting repair, Serve the tray, Four tables, three drinks and Two tables, black coffee

• GPT-6 Lunalast run 2026-11-08
  openai/gpt-6-luna

  44 runs on French press, AeroPress, V60, Portafilter, Grinder, Venn, Bean cosy, Five circles, Pruned shrub, Espresso Rag, Coffee tree, Hopper, Serve the tray, Four tables, three drinks and Two tables, black coffee

• Claude Sonnet 5.5last run 2026-11-08
  anthropic/claude-sonnet-5.5

  30 runs on French press, Fluorocaffeine, Venn, Five circles, Pruned shrub, Stirring spoon, Spoon repair, Serve the tray, Four tables, three drinks and Two tables, black coffee

• Claude Haiku 5.5last run 2026-11-08
  anthropic/claude-haiku-5.5

  48 runs on French press, AeroPress, V60, Portafilter, Grinder, Venn, Bean cosy, Pruned shrub, Espresso Rag, Coffee tree, Hopper, V60 repair, Knitting repair, Serve the tray, Four tables, three drinks and Two tables, black coffee

• Kimi K3last run 2026-10-19
  moonshotai/kimi-k3

  7 runs on French press, Venn and Venn repair

• Pareto 26.9last run 2026-10-19
  unbiased/pareto-26.9

  8 runs on Hopper, Verdict, good press and Verdict, flipped

• Nemotron 3.5 Super VLlast run 2026-10-16
  nvidia/nemotron-3.5-super-vl

  6 runs on French press and Pruned shrub

• Muse Spark Openlast run 2026-10-16
  meta/muse-spark-open

  5 runs on French press and Pruned shrub

• Muse Wonderlast run 2026-10-13
  meta/muse-wonder

  6 runs on French press and Venn

• Qwen3.8 Max Primelast run 2026-10-09
  qwen/qwen3.8-max-prime

  6 runs on Five circles and Pruned shrub

• Pareto 26.10 Previewlast run 2026-10-09
  unbiased/pareto-26.10-preview

  28 runs on French press, AeroPress, V60, Portafilter, Grinder, Five circles, Café order, Pruned shrub, Penrose floor and Espresso Rag

• Step 5 Previewlast run 2026-10-09
  stepfun/step-5-preview

  6 runs on French press and Venn

• Mistral Large 4last run 2026-10-07
  mistralai/mistral-large-4-0

  3 runs on French press and Portafilter

• Ember 1last run 2026-10-04
  fireworks/ember-1

  5 runs on French press and Venn

• GPT-6 Sollast run 2026-10-04
  openai/gpt-6-sol

  14 runs on French press and Venn

• Grok 4.7last run 2026-10-04
  x-ai/grok-4.7

  4 runs on French press and Venn

• Gemini 3.8 Flashlast run 2026-10-04
  google/gemini-3.8-flash

  6 runs on French press, Venn and Pruned shrub

• Paretolast run 2026-10-03
  unbiased/pareto

  7 runs on French press and Pruned shrub

• GPT-5.6 Sollast run 2026-10-03
  openai/gpt-5.6-sol

  6 runs on French press and Pruned shrub

• Qwen3.8 27Blast run 2026-10-03
  qwen/qwen3.8-27b

  6 runs on French press and Pruned shrub

• Qwen3.8 Maxlast run 2026-10-03
  qwen/qwen3.8-max-0902

  5 runs on Caffeine and Pruned shrub

• MiMo v2.6 Prolast run 2026-10-03
  xiaomi/mimo-v2.6-pro

  3 runs on Venn

• Perceptron Mk1.5last run 2026-10-03
  perceptron/perceptron-mk1.5

  9 runs on French press, Venn and Pruned shrub

• Command A+last run 2026-10-03
  cohere/command-a-plus

  9 runs on French press, Venn and Pruned shrub

• Qwen3.8 Flashlast run 2026-09-29
  qwen/qwen3.8-flash

  7 runs on Café table, Venn and Pruned shrub

• Astralast run 2026-09-21
  openai/gpt-6-astra

  4 runs on Boiler

• Union Alphalast run 2026-09-17
  stealth/union-alpha

  1 run on COFFEE route