Coding-focusedOpen Source#7 of 12 in category
Gemini CLI
Google · Launched Jun 2025
Google's open-source terminal agent. With Gemini 3.1 Pro it scores Terminal-Bench 2.1 70.7%.
Visit Gemini CLI →Free tier + API
1
Benchmarks scored
70.7
Peak score
4
Article mentions
Yes
Open source
Benchmark performance
Terminal-Bench 2.1
Held-out, contamination-resistant CLI tasks driven end-to-end in a real terminal. Version 2.1 is the 2026 standard for terminal autonomy.
70.7
Gap to SOTA: -12.7pp (held by Codex CLI (GPT-5.5))Benchmark docs →
Other coding-focused agents
The 12 agents in this category, ranked by peak benchmark.
| Agent | Maker | Launch | Peak | Pricing |
|---|---|---|---|---|
| Kimi K2.5OSS | Moonshot AI | 2026-01 | 1410.0 | Open weights |
| Claude Fable 5 | Anthropic | 2026-05 | 95.0 | $10 / $50 per M tokens |
| Kimi K2.6OSS | Moonshot AI | 2026-04 | 89.6 | Open weights |
| Claude Code | Anthropic | 2025-02 | 88.6 | Claude Max / API |
| Codex CLI | OpenAI | 2025-04 | 83.4 | ChatGPT / API |
| SWE-AgentOSS | Princeton + Stanford | 2024-04 | 74.0 | Open source (MIT) |
| GLM-5.1OSS | Z.ai | 2026-04 | 58.4 | Open weights |
| Cursor Agent | Anysphere | 2025-05 | — | Cursor Pro $20/mo |
| Lovable | Lovable | 2024-11 | — | Freemium |
| OpenCodeOSS | OpenCode | 2025-06 | — | Open source |
Recent coverage
Quick facts
- Type
- Coding-focused
- Maker
- Launch
- 2025-06-25
- Open source
- Yes
- Pricing
- Free tier + API
- Benchmarks scored
- 1
- Article mentions
- 4
- Rank in category
- #7 of 12