Qwen3.8 Omni Report - NL2Repo-Bench: leaderboard

Metric: Score (%). Source: arxiv.org. Saturation forecast: Around July 2028. 6 models tracked.

Top models

#ModelScoreOverall rank
1DeepSeek V4 Flash (0731)54.2#76
2Qwen3.8 Omni Flash48.9#33
3Qwen 3.8 Flash48.1#52
4Claude Opus 4.6 (Max)47.6#61 (Claude Opus 4.6)
5Qwen 3.8 27B42.3#94
6Qwen 3.7 Plus41.1#88

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.

Interactive version: theaggregate.ai/benchmark?slug=qwen3-8-omni-report-nl2repo-bench · How It Works · Data refreshed daily, snapshot 2026-10-14.