Benchmark Almanac

SpireClimb StS2 A10

GPT-6 Astra 34.7% leads since October 2026
GPT-6 Astra 34.7% leads since October 2026
Not in model cards

Agents play Slay the Spire 2 at Ascension 10 through screenshots and mouse and keyboard, 15 runs per character. Scoring is the win rate.

Epoch AI froze the game at v0.107.1, and top human players win about 95 percent of runs.

Made by
Epoch AI
Released
October 2026
Kind
Video games
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last model added
November 2026
Scores refreshed
November 12th, 2026
9
Models scored on its own leaderboard

2 models share the top score of 34.7%

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

GPT-6 Astra leads with 34.7% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

  1. 34.7 GPT-6 Astra
  2. 34.7 GPT-6.1 Terra
  3. 29.3 GPT-6.1 Sol
  4. 17.6 Claude Fable 5.2
  5. 13.3 GPT-6 Sol
  6. 6.67 Claude Opus 5.5
  7. 4.00 Claude Fable 5.1
  8. 2.67 Claude Sonnet 5.5
  9. 0.0 GPT-6 Luna
  1. 1 GPT-6 Astra max; task version 0.3.3_e52e280 34.7%
  2. 2 GPT-6.1 Terra max; task version 0.3.3_447ebe2 34.7%
  3. 3 GPT-6.1 Sol max; task version 0.3.3_e52e280 29.3%
  4. 4 Claude Fable 5.2 max; task version 0.3.3_cd56aef 17.6%
  5. 5 GPT-6 Sol max; task version 0.3.3_e52e280 13.3%
  6. 6 Claude Opus 5.5 max; task version 0.3.3_e52e280 6.67%
  7. 7 Claude Fable 5.1 max; task version 0.3.3_e52e280 4.00%
  8. 8 Claude Sonnet 5.5 max; task version 0.3.3_e52e280 2.67%
  9. 9 GPT-6 Luna max; task version 0.3.3_e52e280 0%

Source: Official SpireClimb StS2 A10 leaderboard

Sources: Official SpireClimb StS2 A10 leaderboard and Epoch AI runs (CC BY 4.0)

#ModelScoreSettingDateSource
1 GPT-6 Astra 34.7% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
2 GPT-6.1 Terra 34.7% max; task version 0.3.3_447ebe2, Epoch Oct 2026 Official leaderboard
3 GPT-6.1 Sol 29.3% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
4 Claude Fable 5.2 17.6% max; task version 0.3.3_cd56aef, Epoch Nov 2026 Official leaderboard
5 GPT-6 Sol 13.3% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
6 Claude Opus 5.5 6.67% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
7 Claude Fable 5.1 4.00% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
8 Claude Sonnet 5.5 2.67% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
9 GPT-6 Luna 0% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-6 Astra 34.7% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
2 GPT-6.1 Terra 34.7% max; task version 0.3.3_447ebe2, Epoch Oct 2026 Official leaderboard
3 GPT-6.1 Sol 29.3% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
4 Claude Fable 5.2 17.6% max; task version 0.3.3_cd56aef, Epoch Nov 2026 Official leaderboard
5 GPT-6 Sol 13.3% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
6 Claude Opus 5.5 6.67% max Sep 2026 Epoch AI run
7 Claude Fable 5.1 4.00% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard
8 Claude Sonnet 5.5 2.67% max Sep 2026 Epoch AI run
9 GPT-6 Luna 0% max; task version 0.3.3_e52e280, Epoch Sep 2026 Official leaderboard

Epoch AI has run 9 models. Switch the scores above to rank them together.

Number one over time Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and Epoch AI’s runs.

OpenAI
Own leaderboard 1 leader
GPT-6 Astra 34.7%
Epoch AI runs 1 leader
GPT-6 Astra 34.7%

Sources: Official SpireClimb StS2 A10 leaderboard and Epoch AI runs (CC BY 4.0)

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Run by Epoch AI Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1

Sources: Official SpireClimb StS2 A10 leaderboard and Epoch AI runs (CC BY 4.0)

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Games and long tasks

All 82 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6 Astra 99.95%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games. Gemini 2.5 Pro 3.90
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress. Llama 4 Scout 7.00
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%