Models | WorkloadBench

Model	Tool	First run	Latest run	Where it appears
Claude Opus 5.5	Claude Code	22 September 2026	22 October 2026	Home: rechecks and new models, deep suite chart Quick suite: real app work, app code per tickets run, explain task, time per run Skills: every measure and task ASD-STE100 tip: answer length Deep suite: score against cost The cache: prompt from the cache Deep suite v2: scores Deep suite v1: tasks solved Muse Wonder: speed Gemini 4 Argon: speed Claude Opus 5.5 recheck: real app work, two Claude Code releases Rechecks: the list GPT-6.1 Sol speed: same day, other models
Claude Haiku 5.5	Claude Code	7 October 2026	16 October 2026	Home: rechecks and new models, deep suite chart Quick suite: app code per tickets run Deep suite: score against cost The cache: prompt from the cache Deep suite v2: scores Deep suite v1: tasks solved Claude Haiku 5.5 vs GPT-6 Luna: speed New models: the list
GPT-6.1 Sol	Codex CLI	29 September 2026	16 October 2026	Home: rechecks and new models, deep suite chart Quick suite: real app work, app code per tickets run, explain task, time per run Skills: every measure and task ASD-STE100 tip: answer length Deep suite: score against cost The cache: prompt from the cache Deep suite v2: scores Deep suite v1: tasks solved Muse Wonder: speed Gemini 4 Argon: speed GPT-6.1 Sol recheck: real app work Rechecks: the list GPT-6.1 Sol speed: seconds and streaming speed, same day, other models
Gemini 4 Argon	Cursor CLI	13 October 2026	16 October 2026	Home: rechecks and new models Quick suite: app code per tickets run Muse Wonder: speed Gemini 4 Argon: speed New models: the list
Muse Wonder	Cursor CLI	16 October 2026	16 October 2026	Home: rechecks and new models Quick suite: app code per tickets run Muse Wonder: speed New models: the list
GPT-6 Luna	Codex CLI	22 September 2026	15 October 2026	Home: rechecks and new models, deep suite chart Quick suite: app code per tickets run, explain task, time per run Skills: every measure and task, other rounds ASD-STE100 tip: answer length Deep suite: score against cost The cache: prompt from the cache Deep suite v2: scores Deep suite v1: tasks solved Claude Haiku 5.5 vs GPT-6 Luna: speed New models: the list
Claude Sonnet 5.5	Claude Code	28 September 2026	7 October 2026	Quick suite: real app work, app code per tickets run, explain task, time per run Skills: every measure and task ASD-STE100 tip: answer length Claude Haiku 5.5 vs GPT-6 Luna: trial runs in the method GPT-6.1 Sol speed: same day, other models
Claude Sonnet 5	Claude Code	22 September 2026	2 October 2026	Quick suite: explain task, time per run Skills: every measure and task ASD-STE100 tip: answer length
GPT-5.6 Luna	Codex CLI	22 September 2026	2 October 2026	Quick suite: explain task, time per run Skills: every measure and task, other rounds ASD-STE100 tip: answer length
Claude Fable 5.1	Claude Code	28 September 2026	30 September 2026	Quick suite: explain task, time per run Skills: other rounds
GPT-5.6 Sol	Codex CLI	28 September 2026	30 September 2026	Quick suite: real app work, app code per tickets run, explain task, time per run Skills: other rounds
GPT-6 Astra	Codex CLI	28 September 2026	30 September 2026	Quick suite: explain task, time per run Skills: other rounds
GPT-6 Sol	Codex CLI	28 September 2026	30 September 2026	Quick suite: real app work, app code per tickets run, explain task, time per run Skills: other rounds