5 models
Ranked by SWE-Bench Multilingual
Reasoning Tools 89.5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

anthropic/claude-opus-5 2026-07-24 1M context $5/M input $25/M output
32 providers
Reasoning Tools 78.3

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

alibaba/qwen3.7-max 2026-05-21 1M context $2.5/M input $7.5/M output
31 providers
Tools JSON 78.3

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

anthropic/claude-sonnet-5 2026-06-30 1M context $2/M input $10/M output
35 providers
Reasoning Tools JSON 78.0

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

xai/grok-4.5 2026-07-08 500K context $2/M input $6/M output
26 providers
Reasoning Tools Open weights 67.7

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

nvidia/nemotron-3-ultra-550b-a55b 2026-06-04 256K context $0.625/M input $3.125/M output
15 providers