One Word, Different Action - Compositional Accuracy: leaderboard
One Word, Different Action (2026) on 408 compositional instances that combine two or three constraints, set exclusion, action inhibition and cardinality, on object-centric robot decision anchors. Exact-match accuracy of the executable decision in percent; higher is better.
Metric: Executable-decision accuracy (%; exact match of the executable decision (object, object set or ordered action sequence) against deterministic ground truth over 85 physical decision anchors collected with a real robot; 408 compositional instances in 102 families that join two or three constraints (exclusion, inhibition, cardinality); temperature 0, at most 512 new tokens, no chain of thought requested; an unmappable output counts as wrong). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5 FP8 | 94.9 | #260 |
| 2 | Mistral 7B Instruct (v0.3) | 83.6 | #6698 |
| 3 | OLMo-2-1124-7B-Instruct | 82.8 | #7377 |
| 4 | Qwen 2.5 7B Instruct | 64.5 | #2583 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=one-word-different-action-compositional-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-12.