8 models
Ranked by SWE-Atlas Codebase QnA
Reasoning Tools JSON 79.1

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

openai/gpt-5.5 2026-04-23 1.05M context $5/M input $30/M output
46 providers
Reasoning Tools 78.4

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 72.9

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

openai/gpt-5.4 2026-03-05 1.05M context $2.5/M input $15/M output
42 providers
Reasoning Tools 71.9

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 70.3

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
Reasoning Tools Open weights 20.5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

zhipuai/glm-5 2026-02-12 204.8K context $1/M input $3.2/M output
37 providers
Tools Open weights 13.1

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

moonshotai/kimi-k2.5 2026-01 262.144K context $0.45/M input $2.25/M output
46 providers
Reasoning Tools Open weights 10.3

Prior MiniMax coding model for agent workflows, office edits, and automation

minimax/MiniMax-M2.5 2026-02-12 204.8K context $0.3/M input $1.2/M output
35 providers