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
Every model the catalog carries a published Artificial Analysis Decision Index v1.0 value for, ranked by that value.
Artificial Analysis scored decision models on its Decision Index v1.0, the first version, and ran every evaluation itself. The index was the weighted average of AA-Omniscience-Decision accuracy and non-hallucination rate (12.5% each), HLE-MultiChoice, When2Call and WildGuardTest (25% each). Version 2.0 replaced it in November 2026; these are its last scores. 19 models in the ModelScale catalog have a published value.
Each point is a model with a published Artificial Analysis Decision Index v1.0 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
19 models with a published Artificial Analysis Decision Index v1.0 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 | 65.2 | |
| 2 | FAGLiDE v1.2 | Fastino | 65.0 |
| 3 | BAelephant-1 | Baseten | 64.7 |
What the benchmark measures and how its value is published, from the source’s own record.
Artificial Analysis Decision Index v1.0 is an external benchmark published by Artificial Analysis Decision Index v1.0. Artificial Analysis scored decision models on its Decision Index v1.0, the first version, and ran every evaluation itself. The index was the weighted average of AA-Omniscience-Decision accuracy and non-hallucination rate (12.5% each), HLE-MultiChoice, When2Call and WildGuardTest (25% each). Version 2.0 replaced it in November 2026; these are its last scores. The source rates its difficulty as weighted average of four decision-model evaluations.
Each model's result is published by Artificial Analysis Decision Index v1.0 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 19 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 | NADrex Max v1.1 | Nace.AI | 63.8 |
| 5 | NADrex Max | Nace.AI | 63.7 |
| 6 | CECeleris-1.1 Decision | Celeris | 60.9 |
| 7 | NADrex v2.0 | Nace.AI | 57.9 |
| 8 | TAJev 1.14 | TypeSafe AI | 57.1 |
| 9 | Perplexity | 56.2 |
| 10 | FAGLiDE | Fastino | 53.9 |
| 11 | Microsoft | 53.8 |
| 12 | Inception | 52.7 |
| 13 | CECeleris-1 Decision | Celeris | 52.3 |
| 14 | NADrex v1.5 | Nace.AI | 50.7 |
| 15 | Liquid AI | 50.3 |
| 16 | Perplexity | 50.2 |
| 17 | CLClef | Cloudflare | 48.6 |
| 18 | CLClef-Flash | Cloudflare | 45.8 |
| 19 | CLClef-Omni | Cloudflare | 44.3 |
Evidence key: Observed
Rows are ordered by the value Artificial Analysis Decision Index v1.0 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.