# Artificial Analysis Decision Index v1.0 leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-aa-decision-index

Every model the catalog carries a published Artificial Analysis Decision Index v1.0 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Weighted average, 0 to 100 |
| Tasks | — |
| Difficulty | Weighted average of four decision-model evaluations |
| Published by | [Artificial Analysis Decision Index v1.0](https://artificialanalysis.ai/articles/artificial-analysis-decision-index) |

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.

## Artificial Analysis Decision Index v1.0 ranking

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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [d1-ultra](https://modelchoice.dev/models/d1-ultra) | Liquid AI | 65.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GLiDE v1.2](https://modelchoice.dev/models/fastino-glide-v1-2) | Fastino | 65.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [elephant-1](https://modelchoice.dev/models/elephant-1) | Baseten | 64.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Drex Max v1.1](https://modelchoice.dev/models/drex-max-v1-1) | Nace.AI | 63.8 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Drex Max](https://modelchoice.dev/models/drex-max) | Nace.AI | 63.7 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Celeris-1.1 Decision](https://modelchoice.dev/models/celeris-1-1-decision) | Celeris | 60.9 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Drex v2.0](https://modelchoice.dev/models/drex-v2-0) | Nace.AI | 57.9 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Jev 1.14](https://modelchoice.dev/models/jev-1-14) | TypeSafe AI | 57.1 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Perplexity Decider v1.2 27B](https://modelchoice.dev/models/pplx-decider-v1-2) | Perplexity | 56.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GLiDE](https://modelchoice.dev/models/fastino-glide) | Fastino | 53.9 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Microsoft-Decision-1](https://modelchoice.dev/models/microsoft-decision-1) | Microsoft | 53.8 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Mercury Decide](https://modelchoice.dev/models/mercury-decide) | Inception | 52.7 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Celeris-1 Decision](https://modelchoice.dev/models/celeris-1-decision) | Celeris | 52.3 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Drex v1.5](https://modelchoice.dev/models/drex-v1-5) | Nace.AI | 50.7 | Observed 2026-11-21 · source benchlm:models |
| 15 | [d1](https://modelchoice.dev/models/liquid-d1) | Liquid AI | 50.3 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Perplexity Decider Flash v1.2 4B](https://modelchoice.dev/models/pplx-decider-flash-v1-2) | Perplexity | 50.2 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Clef](https://modelchoice.dev/models/cloudflare-clef) | Cloudflare | 48.6 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Clef-Flash](https://modelchoice.dev/models/cloudflare-clef-flash) | Cloudflare | 45.8 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Clef-Omni](https://modelchoice.dev/models/cloudflare-clef-omni) | Cloudflare | 44.3 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
