G-IdiomAlign - Multiple-Choice Equivalence - English Targets: leaderboard
Metric: Accuracy (%; source idiom to its meaning-equivalent target-language idiom among four options, the other three typed distractors (literal translation, lexical cue, contextual association), greedy decoding; macro-average over the 8 directions into English). Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 (Thinking) | 66.7 |
| 2 | Gemini 2.5 Pro | 66.53 |
| 3 | DeepSeek V3.2 (Non-reasoning) | 57.84 |
| 4 | Claude Haiku 4.5 | 55.54 |
| 5 | Qwen 3 8B (Thinking) | 39.57 |
| 6 | Qwen 3 8B (Non-reasoning) | 33.95 |
| 7 | Ministral-8B-Instruct-2410 | 30.29 |
Interactive version: theaggregate.ai/benchmark?slug=g-idiomalign-multiple-choice-equivalence-english-targets · How It Works · Data refreshed daily, snapshot 2026-09-26.