Benchmark Almanac

SpireClimb StS2 A10

GPT-6 Astra 34.7% leads since Oct 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 Oct 2026 Video games Last model added Sep 2026 Scores refreshed 31 Oct 2026
Level
Everyday Most adults, without training
Scored
Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers
Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Leaderboard epoch.ai
7
Models scored in Epoch AI data

GPT-6 Astra leads with 34.7%

Best score per model in Epoch AI’s data. Where a model ran with several settings or harnesses, we keep its best.

  1. 34.7 GPT-6 Astra
  2. 29.3 GPT-6.1 Sol
  3. 13.3 GPT-6 Sol
  4. 6.67 Claude Opus 5.5
  5. 4.00 Claude Fable 5.1
  6. 2.67 Claude Sonnet 5.5
  7. 0.0 GPT-6 Luna
  1. 1 GPT-6 Astra max 34.7%
  2. 2 GPT-6.1 Sol max 29.3%
  3. 3 GPT-6 Sol max 13.3%
  4. 4 Claude Opus 5.5 max 6.67%
  5. 5 Claude Fable 5.1 max 4.00%
  6. 6 Claude Sonnet 5.5 max 2.67%
  7. 7 GPT-6 Luna max 0%
#ModelScoreSettingDateSource
1 GPT-6 Astra 34.7% max Sep 2026 Epoch AI
2 GPT-6.1 Sol 29.3% max Sep 2026 Epoch AI
3 GPT-6 Sol 13.3% max Sep 2026 Epoch AI
4 Claude Opus 5.5 6.67% max Sep 2026 Epoch AI
5 Claude Fable 5.1 4.00% max Sep 2026 Epoch AI
6 Claude Sonnet 5.5 2.67% max Sep 2026 Epoch AI
7 GPT-6 Luna 0% max Sep 2026 Epoch AI

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

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

Scores over time

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

Run or collected by Epoch AI Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1 0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1

No lab model card reports it yet

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.

More in Games and long tasks

All 68 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 100%
  • 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%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Scores come from in-game progress or outcomes per title. Nemotron 3 Nano 4B 22.9
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. Gemini 3 Flash 41.9%
  • 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%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. Measures game progress and harmful actions per 100 steps. Muse Spark 2.40