All tasks / Tools
OpenCode
Open-source coding agent with a terminal UI and desktop app that connects to models from any provider, including local ones.
- Anomaly Innovations
- Local or cloud
- Free, open source
Where it ranks
- BCodingCoding agents · Local · via DeepSeek-V4.1-Flash-1017
Ranked by its own benchmark result where it has one; otherwise by the best model it offers.
Facts
- Vendor
- Anomaly Innovations
- Approach
- Coding agents
- Where it runs
- Runs fully on your hardware with local models; cloud models optional
- Interface
- Command line, Desktop app
- Skill level
- Intermediate: some setup or configuration
- Price
- Free, open source
- Pricing notes
- Open source and free with your own provider keys or local models (Ollama, LM Studio, llama.cpp); some free models included. Optional OpenCode Go $10/mo or Go Plus $40/mo for curated models; Zen pay-as-you-go.
- Source code
- Open source (MIT)
- GitHub stars
- 216.3k (18 Oct 2026)
- Last verified
- 18 Oct 2026
Price from opencode.ai, 18 Oct 2026.
Models it gives you
- SClaude Opus 5.5Anthropic · closed
- SGPT-6 AstraOpenAI · closed
- SClaude Sonnet 5.5Anthropic · closed
- AGPT-6.1 SolOpenAI · closed
- BDeepSeek-V4.1-Flash-1017DeepSeek · open weights
- BKimi K3Moonshot AI · open weights
- BQwen3.8-2.4T-A95BAlibaba (Qwen) · open weights
- CGLM-5.3Z.ai · open weights
- CQwen3.8-27BAlibaba (Qwen) · open weights
- CClaude Haiku 5.5Anthropic · closed
- CDeepSeek-V4-Pro-0813DeepSeek · open weights
- CMiniMax-M3MiniMax · open weights
- CGemini 3.1 Pro (Preview)Google · closed
Its own benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Agent Index (v1.5) | 54 | Opencode + GLM-5.3AA label 'Opencode - GLM-5.3 ({'reasoning_effort': 'max'})'; Coding Agent Index v1.5, rank 23 of 42; components (pass@1 avg of 3 attempts): DeepSWE v1.1 61.4%; SWE-Atlas-QnA 59.4%; Terminal-Bench v4 39.9%; read from the page's embedded data; no last-updated date shown | 18 Oct 2026 | artificialanalysis.ai |
| Terminal-Bench 2.0 | 51.7% | OpenCode + Claude Opus 4.5rank 63 of 142 entries; raw accuracy 51.69; entry date 2025-11-24; not marked verified; agent org: Anomaly Innovations; read via the site's leaderboard-read API (page is client-rendered) | 18 Oct 2026 | tbench.ai |