G-IdiomAlign - Gloss-Contrastive Generation (No Gloss): leaderboard
Metric: Acc@0.80 (%; the model writes one target-language idiom for a source idiom, correct when its Qwen3-Embedding-8B cosine similarity to the reference idiom is at least 0.80, greedy decoding, macro-average over 72 translation directions; source idiom only). Source: arxiv.org. Saturation forecast: Around 2030. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 (Thinking) | 24.66 |
| 2 | Claude Haiku 4.5 | 20.47 |
| 3 | DeepSeek V3.2 (Non-reasoning) | 19.9 |
| 4 | Gemini 2.5 Pro | 19.7 |
| 5 | Qwen 3 8B (Thinking) | 14.04 |
| 6 | Ministral-8B-Instruct-2410 | 12.96 |
| 7 | Qwen 3 8B (Non-reasoning) | 11.59 |
Interactive version: theaggregate.ai/benchmark?slug=g-idiomalign-gloss-contrastive-generation-no-gloss · How It Works · Data refreshed daily, snapshot 2026-09-26.