Claude Opus 4.8
Production-available Anthropic flagship. Tops or near-tops Arena overall and coding while remaining the most practical 'max intelligence' Claude for most teams.
When to use it
Coding agents, computer use, and careful long-form reasoning in production.
Watch-outs
Still expensive at max effort; slower than Sonnet for high-volume traffic.
Benchmarks
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.
More from Anthropic
- Claude Fable 5AA 60
Hard coding agents, long computer-use sessions, and high-stakes knowledge work.
- Claude Opus 4.7AA 52
Complex coding agents and careful editorial writing.
- Claude Sonnet 4AA 48
Day-to-day coding copilots, customer agents, and high-volume Claude deployments.