Llama 4 Maverick
Meta's widely deployed open-weight generalist — strong ecosystem, permissive licensing, solid mid-frontier quality.
When to use it
Enterprise self-host, fine-tunes, and cost-controlled chat at scale.
Watch-outs
Trails DeepSeek/MiniMax on newest coding/intelligence composites.
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.