# SpireClimb 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-spire-climb

SpireClimb (Slay the Spire 1 and 2). Every model the catalog carries a published SpireClimb value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Win rate, averaged across the two games, computer-use harness |
| Tasks | 60 Slay the Spire 1 runs (Ascension 20, Heart kill) and 75 Slay the Spire 2 runs (Ascension 10) per model |
| Difficulty | Maximum game difficulty, long-horizon computer use |
| Published by | [SpireClimb (Epoch AI)](https://epoch.ai/benchmarks/spireclimb) |

Epoch AI's SpireClimb has models play Slay the Spire and Slay the Spire 2 at each game's maximum difficulty through a computer-use harness, as an end-to-end test of computer use, long-horizon reasoning and tactical play.

## SpireClimb ranking

12 models with a published SpireClimb 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 | Win rate, averaged across the two games, computer-use harness | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6.2 Astra](https://modelchoice.dev/models/gpt-6-2-astra) | OpenAI | 41.3 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 34.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 23.8 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 22.3 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Fable 5.2](https://modelchoice.dev/models/claude-fable-5-2) | Anthropic | 15.3 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 9.2 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Gemini 4 Hydrogen](https://modelchoice.dev/models/gemini-4-hydrogen) | Google | 7.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 5.8 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 2.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 1.3 | Observed 2026-11-21 · source benchlm:models |
| 11 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 0.0 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 0.0 | 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.
