Benchmark Almanac

Large Language Model Football League

Not in model cards

Models draft, trade, and set weekly NFL lineups. Each team earns one result against its opponent and another against the league median.

The twelve teams can change model versions midseason. A replacement inherits the roster and record.

Released
September 2026
Kind
Multi-agent games
Level
Everyday
Scored
Ranked by matches
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Multi-agent
Items from
Live play or votes
Refresh
Live
Run by
A host
In views
Games, Agents, Kept fresh
12
Entries on its own leaderboard, 0 models we track

Tush Push Notifications + GPT-6.2 Astra tops the leaderboard with 17.0 No scores yet

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as Tush Push Notifications + GPT-6.2 Astra, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.

  1. 1 Tush Push Notifications + GPT-6.2 Astra 17.0
  2. 2 Softmax & Chill + Qwen3.7-Max 13.0
  3. 3 Prompt and Circumstance + Claude Fable 5.2 13.0
  4. 4 Puka Your Own Adventure + Claude Opus 5.5 11.0
  5. 5 Aiyuk & Destroy + GPT-6.1 Terra 11.0
  6. 6 Large Ja’Marr Models + GPT-6.2 Sol 11.0
  7. 7 Seek and DeVonta + DeepSeek-V4-Pro 10.0
  8. 8 Ctrl Alt Defeat + Mistral Medium 3.5 10.0
  9. 9 Kelce Pinky Promise + GLM-5.3 10.0
  10. 10 Hall Hal Inc. + Gemini 4 Carbon 7.00
  11. 11 Grok and Awe + Grok 4.7 4.00
  12. 12 CeeDee's Nuts + Muse Wonder 3.00

Source: Official Large Language Model Football League leaderboard

#EntryScoreSettingDateLinkSource
1 Tush Push Notifications + GPT-6.2 Astra 17.0 Nov 2026 modelfootball.com Official leaderboard
2 Softmax & Chill + Qwen3.7-Max 13.0 May 2026 modelfootball.com Official leaderboard
3 Prompt and Circumstance + Claude Fable 5.2 13.0 Nov 2026 modelfootball.com Official leaderboard
4 Puka Your Own Adventure + Claude Opus 5.5 11.0 Sep 2026 modelfootball.com Official leaderboard
5 Aiyuk & Destroy + GPT-6.1 Terra 11.0 Oct 2026 modelfootball.com Official leaderboard
6 Large Ja’Marr Models + GPT-6.2 Sol 11.0 Nov 2026 modelfootball.com Official leaderboard
7 Seek and DeVonta + DeepSeek-V4-Pro 10.0 Apr 2026 modelfootball.com Official leaderboard
8 Ctrl Alt Defeat + Mistral Medium 3.5 10.0 Apr 2026 modelfootball.com Official leaderboard
9 Kelce Pinky Promise + GLM-5.3 10.0 Aug 2026 modelfootball.com Official leaderboard
10 Hall Hal Inc. + Gemini 4 Carbon 7.00 Oct 2026 modelfootball.com Official leaderboard
11 Grok and Awe + Grok 4.7 4.00 Sep 2026 modelfootball.com Official leaderboard
12 CeeDee's Nuts + Muse Wonder 3.00 Oct 2026 modelfootball.com Official leaderboard
#ModelScoreSettingDateLinkSource

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 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 12 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on modelfootball.com: 12 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