# SpireClimb (Slay the Spire 1 and 2) (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.

Canonical page: https://benchlm.ai/benchmarks/spireclimb

- Category: [Agentic](/agentic)
- Last updated: November 13, 2026

## About SpireClimb

- Year: 2026
- Tasks: 60 Slay the Spire 1 runs (Ascension 20, Heart kill) and 75 Slay the Spire 2 runs (Ascension 10) per model
- Format: Win rate, averaged across the two games, computer-use harness
- Difficulty: Maximum game difficulty, long-horizon computer use
- Paper: [SpireClimb (Epoch AI)](https://epoch.ai/benchmarks/spireclimb)

Models play through a computer-use harness. In Slay the Spire 1 the setting is Ascension 20 with the Act 4 Heart kill: 15 runs on each of the four characters, 60 runs in total. In Slay the Spire 2 it is Ascension 10: 15 runs on each of five characters, 75 runs. Every model plays the same fixed seeds. The SpireClimb score is the average of the two win rates, with both games weighted equally. Epoch froze Slay the Spire 2 at version 0.107.1 so the task stays fixed while the early-access game keeps changing. Top human players win roughly 85% of max-difficulty runs in the first game and about 95% in the second.

SpireClimb is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (9 models)

| Rank | Model | Creator | Score | Who ran it |
|------|-------|---------|-------|-----------|
| 1 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 34.0% | Run by SpireClimb |
| 2 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | OpenAI | 23.8% | Run by SpireClimb |
| 3 | [GPT-6.1 Terra](/models/gpt-6-1-terra) | OpenAI | 22.3% | Run by SpireClimb |
| 4 | [Claude Fable 5.2](/models/claude-fable-5-2) | Anthropic | 19.6% | Run by SpireClimb |
| 5 | [GPT-6 Sol](/models/gpt-6-sol) | OpenAI | 9.2% | Run by SpireClimb |
| 6 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 5.8% | Run by SpireClimb |
| 7 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 2.0% | Run by SpireClimb |
| 8 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | 1.3% | Run by SpireClimb |
| 9 | [GPT-6 Luna](/models/gpt-6-luna) | OpenAI | 0.0% | Run by SpireClimb |

## FAQ

### What does SpireClimb measure?

Whether a model can win full games of Slay the Spire and Slay the Spire 2 at maximum difficulty while operating the game through a computer-use harness. It combines computer use, long-horizon planning and tactical card play.

### Which model leads SpireClimb?

GPT-6 Astra at max effort leads with 34.0%, ahead of GPT-6.1 Sol (23.8%), GPT-6.1 Terra (22.3%) and Claude Fable 5.2 (19.6%). Top human players win roughly 85% to 95% of runs at these settings.

### How is the score calculated?

Epoch averages two win rates: Slay the Spire 1 at Ascension 20 including the Heart (60 runs) and Slay the Spire 2 at Ascension 10 (75 runs). Both games count equally.

## Compare Top Models on SpireClimb

- [GPT-6 Astra vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-gpt-6-astra)
- [GPT-6.1 Sol vs GPT-6.1 Terra](/compare/gpt-6-1-sol-vs-gpt-6-1-terra)
- [GPT-6.1 Terra vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-gpt-6-1-terra)
- [Claude Fable 5.2 vs GPT-6 Sol](/compare/claude-fable-5-2-vs-gpt-6-sol)