Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…
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-AgentOpen 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.

AgentMakerLaunchPeakPricing
Kimi K2.5OSSMoonshot AI2026-011410.0Open weights
Claude CodeAnthropic2025-0288.6Claude Max / API
Codex CLIOpenAI2025-0483.4ChatGPT / API
Kimi K2.6OSSMoonshot AI2026-0480.2Open weights
Gemini CLIOSSGoogle2025-0670.7Free tier + API
GLM-5.1OSSZ.ai2026-0458.4Open weights
OpenCodeOSSOpenCode2025-06Open source
AiderOSSAider2023-05Open 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