Coding-focusedOpen Source#5 of 9 in category
SWE-Agent
Princeton + Stanford · Launched Apr 2024
The academic agent that defined the Agent-Computer Interface for fixing GitHub issues; the open baseline behind SWE-bench.
Visit SWE-Agent →Open source (MIT)
1
Benchmarks scored
74.0
Peak score
1
Article mentions
Yes
Open source
Benchmark performance
SWE-Bench Verified
OpenAI-verified 500-issue subset of SWE-Bench. Approaching saturation in 2026 - most frontier models clear 80%+.
74.0
Gap to SOTA: -21.0pp (held by Claude Fable 5)Benchmark docs →
Other coding-focused agents
The 9 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 Code | Anthropic | 2025-02 | 88.6 | Claude Max / API |
| Codex CLI | OpenAI | 2025-04 | 83.4 | ChatGPT / API |
| Kimi K2.6OSS | Moonshot AI | 2026-04 | 80.2 | Open weights |
| Gemini CLIOSS | 2025-06 | 70.7 | Free tier + API | |
| GLM-5.1OSS | Z.ai | 2026-04 | 58.4 | Open weights |
| OpenCodeOSS | OpenCode | 2025-06 | — | Open source |
| AiderOSS | Aider | 2023-05 | — | Open source (Apache-2) |
Recent coverage
Quick facts
- Type
- Coding-focused
- Maker
- Princeton + Stanford
- Launch
- 2024-04-15
- Open source
- Yes
- Pricing
- Open source (MIT)
- Benchmarks scored
- 1
- Article mentions
- 1
- Rank in category
- #5 of 9