10 models
Ranked by SWE-Bench Pro
Reasoning Tools 64.3

Stronger Opus tier for advanced software work and high-stakes reasoning

anthropic/claude-opus-4-7 2026-04-16 1M context $5/M input $25/M output
40 providers
Reasoning Tools JSON 59.1

Agent-ready GPT for coding and computer-use workflows at a lower cost

openai/gpt-5.4 2026-03-05 1.05M context $2.5/M input $15/M output
42 providers
Reasoning Tools 51.9

High-end Claude for difficult coding, planning, and slower expert reasoning

anthropic/claude-opus-4-6 2026-02-05 1M context $5/M input $25/M output
37 providers
Reasoning Tools 43.6

Balanced Claude model for coding, analysis, agent workflows, and cost control

anthropic/claude-sonnet-4-5 2025-09-29 200K context $3/M input $15/M output
20 providers
Reasoning Tools JSON 43.3

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

google/gemini-3-pro-preview 2025-11-18 1.04858M context $0.57/M input $3.43/M output
10 providers
Tools 41.8

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

openai/gpt-5 2025-08-07 400K context $1.25/M input $10/M output
30 providers
Reasoning Tools 39.5

Fast Claude lane for lightweight agents, office tasks, and responsive chat

anthropic/claude-haiku-4-5 2025-10-15 200K context $1/M input $5/M output
23 providers
Reasoning Tools JSON 34.6

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

google/gemini-3-flash-preview 2025-12-17 1.04858M context $0.5/M input $3/M output
25 providers
Reasoning Tools 29.9

Reliable GPT generation for broad coding, writing, and tool-assisted product work

openai/gpt-5.2 2025-12-11 400K context $1.75/M input $14/M output
33 providers
Reasoning Tools 14.9

Claude workhorse for coding agents, careful analysis, and production cost control

anthropic/claude-sonnet-4-6 2026-02-17 1M context $3/M input $15/M output
45 providers