Benchmark Almanac

Eleusis

GPT-6 Sol 82.2% leads since September 2026
Not in model cards

Agents play cards to discover a hidden rule. The scorer tests whether a proposed rule makes the same decisions as the hidden rule.

On October 7, 2026, teams of eight or sixteen GPT-6 Sol agents solved all 20 episodes in the team size experiment. A separate experiment compared GPT-6 Sol, GPT-6 Luna and DeepSeek V4.1 Flash.

Released
June 2026
Kind
Multi-agent games
Level
Competition
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions, Text
Interaction
Multi-agent
Environment
Eleusis
Refresh
One fixed set
Run by
Anyone
In views
Games, Agents
Strongest model tested
GPT-6 Sol #13 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
3
Models scored in its paper

GPT-6 Sol leads with 82.2% among models released by September 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-6 Sol Three-agent cooperative team with broadcast messaging 82.2%
  2. 2 DeepSeek V4.1 Flash Three-agent cooperative team with broadcast messaging 48.9%
  3. 3 GPT-6 Luna Three-agent cooperative team with broadcast messaging 48.9%

Source: The Eleusis paper

#ModelScoreSettingDateSource
1 GPT-6 Sol 82.2% Three-agent cooperative team with broadcast messaging Sep 2026 Official leaderboard
2 DeepSeek V4.1 Flash 48.9% Three-agent cooperative team with broadcast messaging Sep 2026 Official leaderboard
3 GPT-6 Luna 48.9% Three-agent cooperative team with broadcast messaging Sep 2026 Official leaderboard

2 models have held number one in the benchmark’s paper since its release in June 2026

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

DeepSeek OpenAI
Benchmark paper Not tested since Sep 2026
GPT-6 Sol 82.2%

Source: The Eleusis paper

Scores over time

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

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6 Sol DeepSeek V4.1 Flash 0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6 Sol DeepSeek V4.1 Flash

Source: Official Eleusis 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

All 261 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

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (3 entries).
  • Note Models scored Only 3 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6 Luna.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-6 Sol (#13).
  • Pass Headroom The best is 82.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on nphard.io: 3 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.

How we check