Mastermind (Prime Intellect)
Models guess a hidden sequence and receive feedback after each turn. The default evaluation uses 50 games and rewards success, speed, and deductions.
The highest public hub mean reward was 1.62 for gpt-5 on 5 examples on October 15th, 2025. The hub also lists gpt-oss-120b, gpt-5-mini, gpt-5-nano.
- Made by
- Prime Intellect
- Released
- October 2025
- Kind
- Puzzles and chess
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Mastermind
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
GPT-5 leads with 1.62 among models released by September 2025
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 September 2025, 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 0.1.2, 5 examples 1.62
- 2 gpt-oss-120b 0.1.2, 5 examples 1.62
- 3 GPT-5 mini 0.1.2, 5 examples 1.54
- 4 GPT-5 nano 0.1.2, 5 examples 1.38
- 5 GLM-4.6 0.1.2, 5 examples 1.21
- 6 Claude Sonnet 4.5 0.1.2, 5 examples 0.75
- 7 Kimi K2 Sep 2025, 0.1.2, 5 examples 0.70
- 8 GLM-4.5-Air 0.1.2, 5 examples 0.52
- 9
DeepSeek-V3.2-Exp 0.1.2, 5 examples 0.50
- 10 GPT-4.1 0.1.2, 5 examples 0.49
- 11
DeepSeek-V3.1-Terminus 0.1.2, 5 examples 0.48
- 12
Llama 3.3 70B Instruct 0.1.2, 5 examples 0.39
Source: Official Mastermind (Prime Intellect) leaderboard
| # | Model | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | GPT-5 | 1.62 | 0.1.2, 5 examples | Aug 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 2 | gpt-oss-120b | 1.62 | 0.1.2, 5 examples | Aug 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 3 | GPT-5 mini | 1.54 | 0.1.2, 5 examples | Aug 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 4 | GPT-5 nano | 1.38 | 0.1.2, 5 examples | Aug 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 5 | GLM-4.6 | 1.21 | 0.1.2, 5 examples | Sep 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 6 | Claude Sonnet 4.5 | 0.75 | 0.1.2, 5 examples | Sep 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 7 | Kimi K2 Sep 2025 | 0.70 | 0.1.2, 5 examples | Sep 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 8 | GLM-4.5-Air | 0.52 | 0.1.2, 5 examples | Jul 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 9 | | 0.50 | 0.1.2, 5 examples | Sep 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 10 | GPT-4.1 | 0.49 | 0.1.2, 5 examples | Apr 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 11 | | 0.48 | 0.1.2, 5 examples | Sep 2025 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
| 12 | | 0.39 | 0.1.2, 5 examples | Dec 2024 | Oct 2025 | app.primeintellect.ai | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Mastermind (Prime Intellect) 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 Mastermind (Prime Intellect) 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 14 months ago, in September 2025, for GLM-4.6. 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 (12 entries).
- Pass Models scored 12 models we track.
- Warning Newest score The newest came 14 months ago, in September 2025, for GLM-4.6.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on app.primeintellect.ai: 22 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.