Anthropic's production workhorse: near-Opus coding quality at better latency and cost for most apps.
Day-to-day coding copilots, customer agents, and high-volume Claude deployments.
Ceiling is below Opus/Fable on the hardest agentic tasks.
Human preference ranking from blind pairwise chats. Higher is better; top frontier models cluster within ~50–80 Elo.
Artificial Analysis composite across agents, coding, science, and general evaluations (v4.1 weighting).
Percent of real GitHub issues resolved end-to-end. Strong signal for agentic coding usefulness.
PhD-level science questions. Separates frontier reasoning models better than saturated knowledge tests.
Harder multi-choice knowledge/reasoning suite than classic MMLU.
Frontier closed-ended academic difficulty across many domains.
Hard coding agents, long computer-use sessions, and high-stakes knowledge work.
Coding agents, computer use, and careful long-form reasoning in production.
Complex coding agents and careful editorial writing.