Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
external benchmark
Artificial Analysis Decision Index v2.1. Every model the catalog carries a published Artificial Analysis Decision Index value for, ranked by that value.
Artificial Analysis scores decision models on its Decision Index and runs every evaluation itself. Version 2.1 is the weighted average of six Decision Scores: AA-Paperclip document decisions (30%), EvalSafe-O*NET-AA workplace judgement, AA-Omniscience-Decision v1.1, HLE-MultiChoice v1.1 and AA-Symmetry v1.1 decision invariance (15% each), and When2Call tool calling (10%). 22 models in the ModelScale catalog have a published value.
Each point is a model with a published Artificial Analysis Decision Index value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
22 models with a published Artificial Analysis Decision Index value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Weighted average, 0 to 100 |
|---|---|---|---|
| 1 | Liquid AI | 74.8 | |
| 2 | NADrex Max v1.1 | Nace.AI | 72.6 |
| 3 | FAGLiDE v1.2 | Fastino | 72.5 |
What the benchmark measures and how its value is published, from the source’s own record.
Artificial Analysis Decision Index (Artificial Analysis Decision Index v2.1) is an external benchmark published by Artificial Analysis Decision Index v2.1 methodology. Artificial Analysis scores decision models on its Decision Index and runs every evaluation itself. Version 2.1 is the weighted average of six Decision Scores: AA-Paperclip document decisions (30%), EvalSafe-O*NET-AA workplace judgement, AA-Omniscience-Decision v1.1, HLE-MultiChoice v1.1 and AA-Symmetry v1.1 decision invariance (15% each), and When2Call tool calling (10%). The source rates its difficulty as weighted average of six decision-model evaluations.
Each model's result is published by Artificial Analysis Decision Index v2.1 methodology as weighted average, 0 to 100. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 22 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | BAmammoth-1 | Baseten | 71.4 |
| 5 | Liquid AI | 70.6 |
| 6 | Perplexity | 70.4 |
| 7 | Perplexity | 69.8 |
| 8 | Liquid AI | 68.7 |
| 9 | SUSubQ Snap 1.1 | Subquadratic | 67.9 |
| 10 | BAelephant-1 | Baseten | 66.4 |
| 11 | TAJev 1.14 | TypeSafe AI | 66.2 |
| 12 | 66.0 |
| 13 | Perplexity | 64.1 |
| 14 | Inception | 62.1 |
| 14 | Microsoft | 62.1 |
| 16 | CECeleris-1.1 Decision | Celeris | 62.0 |
| 17 | NADrex v2.0 | Nace.AI | 61.6 |
| 18 | Liquid AI | 60.8 |
| 19 | CLClef | Cloudflare | 60.3 |
| 20 | OpenAI | 60.2 |
| 21 | Perplexity | 60.1 |
| 22 | CLClef-Omni | Cloudflare | 57.8 |
Evidence key: Observed
Rows are ordered by the value Artificial Analysis Decision Index v2.1 methodology published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.