# Artificial Analysis Decision Index 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://modelscale.dev/leaderboards/benchmarks/external-aa-decision-index-v2

Artificial Analysis Decision Index v2.1. Every model the catalog carries a published Artificial Analysis Decision Index value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Weighted average, 0 to 100 |
| Tasks | — |
| Difficulty | Weighted average of six decision-model evaluations |
| Published by | [Artificial Analysis Decision Index v2.1 methodology](https://artificialanalysis.ai/evaluations/artificial-analysis-decision-index) |

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%).

## Artificial Analysis Decision Index ranking

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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [d1.2-ultra](https://modelscale.dev/models/liquid-d1-2-ultra) | Liquid AI | 74.8 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Drex Max v1.1](https://modelscale.dev/models/drex-max-v1-1) | Nace.AI | 72.6 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GLiDE v1.2](https://modelscale.dev/models/fastino-glide-v1-2) | Fastino | 72.5 | Observed 2026-11-21 · source benchlm:models |
| 4 | [mammoth-1](https://modelscale.dev/models/mammoth-1) | Baseten | 71.4 | Observed 2026-11-21 · source benchlm:models |
| 5 | [d1-ultra](https://modelscale.dev/models/d1-ultra) | Liquid AI | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Perplexity Decider v1.3 27B](https://modelscale.dev/models/pplx-decider-v1-3) | Perplexity | 70.4 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Perplexity Decider v1.2 27B](https://modelscale.dev/models/pplx-decider-v1-2) | Perplexity | 69.8 | Observed 2026-11-21 · source benchlm:models |
| 8 | [d1.2](https://modelscale.dev/models/liquid-d1-2) | Liquid AI | 68.7 | Observed 2026-11-21 · source benchlm:models |
| 9 | [SubQ Snap 1.1](https://modelscale.dev/models/subq-snap-1-1) | Subquadratic | 67.9 | Observed 2026-11-21 · source benchlm:models |
| 10 | [elephant-1](https://modelscale.dev/models/elephant-1) | Baseten | 66.4 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Jev 1.14](https://modelscale.dev/models/jev-1-14) | TypeSafe AI | 66.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini Decision 1](https://modelscale.dev/models/gemini-decision-1) | Google | 66.0 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Perplexity Decider Flash v1.3 4B](https://modelscale.dev/models/pplx-decider-flash-v1-3) | Perplexity | 64.1 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Mercury Decide](https://modelscale.dev/models/mercury-decide) | Inception | 62.1 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Microsoft-Decision-1](https://modelscale.dev/models/microsoft-decision-1) | Microsoft | 62.1 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Celeris-1.1 Decision](https://modelscale.dev/models/celeris-1-1-decision) | Celeris | 62.0 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Drex v2.0](https://modelscale.dev/models/drex-v2-0) | Nace.AI | 61.6 | Observed 2026-11-21 · source benchlm:models |
| 18 | [d1](https://modelscale.dev/models/liquid-d1) | Liquid AI | 60.8 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Clef](https://modelscale.dev/models/cloudflare-clef) | Cloudflare | 60.3 | Observed 2026-11-21 · source benchlm:models |
| 20 | [GPT-6 Luna (Decisions)](https://modelscale.dev/models/gpt-6-luna-decisions) | OpenAI | 60.2 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Perplexity Decider Flash v1.2 4B](https://modelscale.dev/models/pplx-decider-flash-v1-2) | Perplexity | 60.1 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Clef-Omni](https://modelscale.dev/models/cloudflare-clef-omni) | Cloudflare | 57.8 | 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.
