SWE-QA (Multi-Hop Code) - Interacting Entities: leaderboard
SWE-QA (2026) asks multiple-choice questions that need several pieces of code from real Python repositories, with the relevant code chunks supplied; questions and distractors were generated with a small LLM. Accuracy on questions about two entities interacting across three code chunks, in percent (chance 25); higher is better.
Metric: Accuracy (%) on the 4,488 Interacting-Entity questions, which follow two entities interacting across three chunks, of SWE-QA, multi-hop multiple-choice questions (four options) about the source of 12 SWE-bench Python repositories, generated with Llama-3.2-3B-Instruct; oracle setting (only the relevant code chunks), zero-shot, labels after the 66-item consensus correction; chance 25; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.3 70B Instruct | 69.98 | #1385 |
| 2 | Gemma 3 4B (IT) | 68.6 | #4139 |
| 3 | Qwen 3 4B Instruct | 65.41 | #1696 |
| 4 | Qwen3-4B-Thinking (SWE-QA checkpoint unspecified) | 54.81 | |
| 5 | GPT-OSS-20B | 53.83 | #1183 |
| 6 | SWE-QA DeepSeek-R1 (checkpoint unspecified) | 53.58 | |
| 7 | Phi-4-mini (Thinking) | 50.35 | |
| 8 | Phi-4 Mini Instruct | 47.9 | #6631 |
| 9 | Qwen 3 1.7B | 43.18 | #5860 |
| 10 | DeepSeek R1 Distill Qwen 1.5B | 39.14 | #9215 |
| 11 | SmolLM2-1.7B-Instruct | 29.94 | #9154 |
| 12 | SmolLM2-360M-Instruct | 20.61 | #9529 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=swe-qa-multi-hop-code-interacting-entities · How It Works · Data refreshed daily, snapshot 2026-11-21.