Live-SWE-agent
Benchmarks & Leaderboards · Free + paid
Can software engineering agents self-evolve on the fly? A living benchmark
At a glance
- Korean
- None (English and a few others only)
What is Live-SWE-agent?
Live-SWE-agent is introduced as the first "live" software agent that keeps evolving itself at runtime while solving real software problems. It starts with limited tools such as bash commands, and at each step it either runs a command or creates a custom tool (an executable script) that helps solve the problem. After receiving environment feedback, it reflects on previous steps and decides whether to create a tool, repeating this process. The leaderboard compares models on SWE-bench Verified and SWE-Bench Pro using the same Live-SWE-agent scaffold.
- Automatically creates custom tools (scripts) at runtime
- Reflects on previous steps after environment feedback and decides whether to create a tool
- SWE-bench Verified leaderboard
- SWE-Bench Pro leaderboard
- Verified result badge (✓)
- Filter by proprietary or open-source model type
- Shows resolve rate and average cost; scores are submitted with the same scaffold
Pricing
Free (public benchmark/leaderboard)
Mostly free leaderboards/datasets released for academic and community purposes
Estimate based on AI knowledge - please verify on the official site
AI tools similar to Live-SWE-agent (alternatives)
Live-SWE-agent vs. alternatives at a glance
| AI | Pricing | Combos on the map | Connected tools | Free | Cheapest monthly | Korean |
|---|---|---|---|---|---|---|
| Live-SWE-agent | Free + paid | 0 | 12 | — | — | No |
| Aider Leaderboard | Free + paid | 0 | 12 | — | — | No |
| CORE-Bench Hard | Free + paid | 0 | 12 | — | — | No |
| SWE-bench | Free + paid | 0 | 5 | — | — | No |
| SWE-bench Multilingual | Free + paid | 0 | 5 | — | — | No |
0 of these 5 tools have a free plan.
Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.
Live-SWE-agent on AI Galaxy Map
- One of 27 AI tools in the Benchmarks & Leaderboards field.
- Connected to 12 other tools — #1 in its field.
Frequently asked questions
Can I use Live-SWE-agent for free?
Free (public benchmark/leaderboard). Prices can change, so check the official site before paying.
What AI can I use instead of Live-SWE-agent?
Tools that do the same job, such as Aider Leaderboard, CORE-Bench Hard, SWE-bench, SWE-bench Multilingual, are connected to it on the map.
Can I use Live-SWE-agent in Korean?
None (English and a few others only)
Sources (official pages)
Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.