Models
22 models so far, most recently run first. Each page has every task the model ran, with every check and what each run did.
- Pareto 26.10 Previewlast run 2026-10-02
unbiased/pareto-26.10-preview3 runs on French press
- Paretolast run 2026-10-01
unbiased/pareto6 runs on French press
- Opus 5.5last run 2026-10-01
anthropic/claude-opus-5.511 runs on French press, Venn and Pruned shrub
- DeepSeek 4.1 Flashlast run 2026-09-29
deepseek/deepseek-v4.1-flash31 runs on French press, COFFEE route, Caffeine, Boiler, Café table, Fluorocaffeine, Venn, Triangle wave, Café order and Pruned shrub
- Qwen3.8 Flashlast run 2026-09-29
qwen/qwen3.8-flash7 runs on Café table, Venn and Pruned shrub
- GPT-6 Lunalast run 2026-09-29
openai/gpt-6-luna6 runs on Venn and Pruned shrub
- Gemini 3.8 Flashlast run 2026-09-29
google/gemini-3.8-flash4 runs on Venn and Pruned shrub
- Claude Sonnet 5.5last run 2026-09-29
anthropic/claude-sonnet-5.59 runs on French press, Venn and Pruned shrub
- GPT-6 Sollast run 2026-09-27
openai/gpt-6-sol13 runs on Venn
- Perceptron Mk1.5last run 2026-09-27
perceptron/perceptron-mk1.56 runs on French press and Venn
- Command A+last run 2026-09-27
cohere/command-a-plus6 runs on French press and Venn
- GLM 5.3 FlashXlast run 2026-09-25
z-ai/glm-5.3-flashx11 runs on French press, COFFEE route and Venn
- Kimi K3last run 2026-09-25
moonshotai/kimi-k33 runs on Venn
- Ember 1last run 2026-09-25
fireworks/ember-13 runs on Venn
- Grok 4.7last run 2026-09-25
x-ai/grok-4.73 runs on Venn
- MiMo v2.6 Prolast run 2026-09-25
xiaomi/mimo-v2.6-pro2 runs on Venn
- Qwen3.8 Max Primelast run 2026-09-25
qwen/qwen3.8-max-prime3 runs on Pruned shrub
- Sollast run 2026-09-22
openai/gpt-5.6-sol4 runs on French press
- Qwen3.8 27Blast run 2026-09-22
qwen/qwen3.8-27b4 runs on French press
- Qwen3.8 Maxlast run 2026-09-21
qwen/qwen3.8-max-09024 runs on Caffeine
- Astralast run 2026-09-21
openai/gpt-6-astra4 runs on Boiler
- Union Alphalast run 2026-09-17
stealth/union-alpha1 run on COFFEE route