# ARC-AGI-3 Provider Adapter leaderboard

Reasoning 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/reasoning-arc-agi3-provider-adapter

ARC-AGI-3 Semi-Private: Provider Adapter harness. Every model the catalog carries a published ARC-AGI-3 Provider Adapter value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Reasoning |
| Measure | — |
| Tasks | — |
| Difficulty | — |
| Published by | [ARC Prize verified ARC-AGI-3 results](https://arcprize.org/leaderboard) |

ARC Prize verified interactive reasoning results using a provider-specific stateful adapter, kept separate from Standard harness results.

## ARC-AGI-3 Provider Adapter ranking

8 models with a published ARC-AGI-3 Provider Adapter 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 | ARC-AGI-3 Provider Adapter | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 98.55 | Observed 2026-10-23 · source benchlm:models |
| 2 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 97.30 | Observed 2026-10-23 · source benchlm:models |
| 3 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 96.18 | Observed 2026-10-23 · source benchlm:models |
| 4 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 35.00 | Observed 2026-10-23 · source benchlm:models |
| 5 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 23.03 | Observed 2026-10-23 · source benchlm:models |
| 6 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 7.02 | Observed 2026-10-23 · source benchlm:models |
| 7 | [Claude Haiku 5.5](https://modelscale.dev/models/claude-haiku-5-5) | Anthropic | 2.82 | Observed 2026-10-23 · source benchlm:models |
| 8 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | 0.59 | Observed 2026-10-23 · 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.