Models & benchmarks
Model matrix
Every model each coding agent supports, with context windows, pricing, and SWE-bench / HumanEval scores side by side.
Last verified: April 2026
Benchmark scores
Higher is better. SWE-bench Verified measures end-to-end task completion on real GitHub issues; HumanEval measures Python function synthesis.
Sources: official SWE-bench Verified leaderboard and provider-published HumanEval scores.
Supported models per agent
Claude Code
Learn more →| Model | Provider | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| Claude Sonnet 4.6Default | Anthropic | 1M | $3 | $15 |
| Claude Opus 4.7 | Anthropic | 1M | $5 | $25 |
| Claude Opus 4.6 | Anthropic | 1M | $5 | $25 |
| Claude Opus 4.5 | Anthropic | 200K | $5 | $25 |
| Claude Opus 4.1 | Anthropic | 200K | $15 | $75 |
| Claude Sonnet 4.5 | Anthropic | 200K | $3 | $15 |
| Claude Haiku 4.5 | Anthropic | 200K | $1 | $5 |
Claude Code defaults to Sonnet 4.6 (1M context). Opus 4.7 is the strongest Anthropic model for complex agentic coding. Haiku 4.5 is the fast, cheap option. Older Opus 4 / Sonnet 4 / Haiku 3.5 are deprecated and being removed.
Cursor
Learn more →| Model | Provider | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| Composer-1 (in-house)Default | Cursor | 200K | Bundled | Bundled |
| Claude Sonnet 4.6 | Anthropic | 1M | Bundled | Bundled |
| Claude Opus 4.7 | Anthropic | 1M | Bundled | Bundled |
| Claude Haiku 4.5 | Anthropic | 200K | Bundled | Bundled |
| GPT-5 | OpenAI | 400K | Bundled | Bundled |
| GPT-5 Codex | OpenAI | 400K | Bundled | Bundled |
| Gemini 3.1 Pro | 1M | Bundled | Bundled | |
| Gemini 3 Flash | 1M | Bundled | Bundled |
Models bundled in the Cursor Pro subscription ($20/mo). Power users add their own API keys to bypass quota.
GitHub Copilot
Learn more →| Model | Provider | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| GPT-5Default | OpenAI | 400K | Bundled | Bundled |
| GPT-5 mini | OpenAI | 400K | Bundled | Bundled |
| Claude Sonnet 4.6 | Anthropic | 1M | Bundled | Bundled |
| Claude Opus 4.7 | Anthropic | 1M | Bundled | Bundled |
| Claude Haiku 4.5 | Anthropic | 200K | Bundled | Bundled |
| Gemini 3.1 Pro | 1M | Bundled | Bundled | |
| Gemini 3 Flash | 1M | Bundled | Bundled | |
| GPT-4.1 | OpenAI | 128K | Bundled | Bundled |
Model picker available on Pro, Business, and Enterprise plans. Free tier limited to default model.
Gemini CLI
Learn more →| Model | Provider | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| Gemini 3.1 Pro (Preview)Default | 1M | $2 | $12 | |
| Gemini 3 Flash (Preview) | 1M | $0.5 | $3 | |
| Gemini 3.1 Flash-Lite (Preview) | 1M | $0.25 | $1.5 | |
| Gemini 2.5 Pro | 1M | $1.25 | $10 | |
| Gemini 2.5 Flash | 1M | $0.3 | $2.5 |
Free tier via personal Google account: 60 requests/min, 1,000 requests/day on Gemini 3.1 Pro Preview. Gemini 3.1 Pro pricing tiers: $2/$12 for prompts ≤200K tokens, $4/$18 above.
OpenCode
Learn more →| Model | Provider | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| Any provider via API keyDefault | BYOK | Provider-defined | Bundled | Bundled |
| Claude Sonnet 4.6 | Anthropic | 1M | $3 | $15 |
| Claude Opus 4.7 | Anthropic | 1M | $5 | $25 |
| Claude Haiku 4.5 | Anthropic | 200K | $1 | $5 |
| GPT-5 | OpenAI | 400K | $5 | $20 |
| Gemini 3.1 Pro | 1M | $2 | $12 | |
| Local Ollama models | Ollama | 32K | Free | Free |
OpenCode is a TUI shell — pricing follows whichever provider key you supply. Local Ollama models are free but cap out around 32k context.
Prices in USD per 1M tokens. Pricing changes — verify on each provider's official page before relying on it.