SpireBench (HermesBridge trial-v0)
Models play Slay the Spire 2 from structured game states. Each plays all five characters at the base difficulty, with one run per character.
The maker reports floor statistics for five models. The 25 run records list 22 deaths and three stalls. No run ended in victory.
- Made by
- Kareem
- Released
- April 2026
- Kind
- Video games
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Slay the Spire 2
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-5.5 #21 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
GPT-5.5 leads with 28.0 among models released by April 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-5.5 A0-zero-shot 28.0
- 2 Claude Opus 4.7 A0-zero-shot 23.0
- 3
DeepSeek-V4-Pro A0-zero-shot 20.0
- 4
Gemini 3.1 Pro A0-zero-shot 17.0
- 5 GLM-5.1 A0-zero-shot 15.0
Source: Official SpireBench (HermesBridge trial-v0) leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 28.0 | A0-zero-shot, HermesBridge | Apr 2026 | Official leaderboard |
| 2 | Claude Opus 4.7 | 23.0 | A0-zero-shot, HermesBridge | Apr 2026 | Official leaderboard |
| 3 | | 20.0 | A0-zero-shot, HermesBridge | Apr 2026 | Official leaderboard |
| 4 | | 17.0 | A0-zero-shot, HermesBridge | Feb 2026 | Official leaderboard |
| 5 | GLM-5.1 | 15.0 | A0-zero-shot, HermesBridge | Apr 2026 | Official leaderboard |
3 models have held number one on the official leaderboard since its release in April 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SpireBench (HermesBridge trial-v0) leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SpireBench (HermesBridge trial-v0) leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More 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-6.2 Astra 100%
- 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%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for DeepSeek-V4-Pro. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (5 entries).
- Pass Models scored 5 models we track.
- Warning Newest score The newest came 7 months ago, in April 2026, for DeepSeek-V4-Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on spirebench.com: 5 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.