InstrEditBench (Multi Turn; Two Shot) - Code ROUGE-L: leaderboard
ROUGE-L (0-1) against reference edited text; InstrEditBench Code, multi turn, two shot; 90/10 train-test split. Multi-turn applies requests cumulatively on 100 randomly sampled multi-turn items per domain. FineEdit trained derivatives remain separate from their Llama/Qwen bases; higher is better.
Metric: ROUGE-L (0-1) against reference edited text; InstrEditBench Code, multi turn, two shot; 90/10 train-test split. Multi-turn applies requests cumulatively on 100 randomly sampled multi-turn items per domain. FineEdit trained derivatives remain separate from their Llama/Qwen bases; higher is better.. Source: aclanthology.org. Saturation forecast: Around January 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.0 Flash | 0.63 | #332 |
| 2 | Gemini 1.5 Flash | 0.34 | #623 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=instreditbench-multi-turn-two-shot-code-rouge-l · How It Works · Data refreshed daily, snapshot 2026-10-16.