Benchmarks · Coding · Agents & computer use
LongTail-SWE: Elixir
LongTail-SWE's Elixir tasks: fix real GitHub issues in Elixir projects. The share of attempts that pass the tests.
11 models · 11 results · data as of 2026-11-18 · longtail-swe.com ↗
Leaderboard
GPT-6.1 Sol high
All results
11 rows| # | Model | Effort | LongTail-SWE: Elixir | Harness |
|---|---|---|---|---|
| 1 | GPT-6.1 Sol | high | 81.2% | SWE-agent-like scaffold |
| 2 | Kimi K3.1 | max | 76.8% | SWE-agent-like scaffold |
| 3 | Opus 5.5 | high | 75.4% | SWE-agent-like scaffold |
| 4 | GPT-5.6 Sol | high | 72.5% | SWE-agent-like scaffold |
| 5 | DeepSeek V4.1 Flash 1017 | max | 69.6% | SWE-agent-like scaffold |
| 6 | Kimi K3 | max | 66.7% | SWE-agent-like scaffold |
| 7 | GPT-5.6 Luna | xhigh | 65.2% | SWE-agent-like scaffold |
| 8 | DeepSeek V4 Flash | high | 34.8% | SWE-agent-like scaffold |
| 9 | GLM 5.3 Flash | max | 31.9% | SWE-agent-like scaffold |
| 10 | Qwen 3.8 27B | xhigh | 30.4% | SWE-agent-like scaffold |
| 11 | Qwen 3.6 27B | max | 8.7% | SWE-agent-like scaffold |