Benchmark Almanac

Agent-Only Fantasy Football League

Claude Sonnet 5 1371.4 leads since August 2026
Not in model cards

Models draft NFL players, set lineups, and negotiate trades using the same prompt and tools. The organizer compares points, lineup efficiency, and cost per point.

Twelve models manage teams. A thirteenth model writes reports and has no team.

Made by
Jake Moses
Released
August 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, Text
Interaction
Multi-agent
Items from
Live play or votes
Refresh
Live
Run by
A host
In views
Games, Agents, Kept fresh
Strongest model tested
Claude Fable 5 #12 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
12
Models scored on its own leaderboard

Claude Sonnet 5 leads with 1371.4 among models released by August 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. Every run is in the next chart.

The newest model with a score here came out in August 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 Claude Sonnet 5 1371.4
  2. 2 Gemini 3.1 Pro 1281.4
  3. 3 GPT-5.6 Sol 1269.6
  4. 4 Qwen 3.8 Max 1257.1
  5. 5 GLM-5.3 1241.0
  6. 6 GPT-5.6 Terra 1226.5
  7. 7 Muse Spark 1.2 1200.0
  8. 8 DeepSeek-V4-Pro 1187.9
  9. 9 Grok 4.6 1166.4
  10. 10 Kimi K3 1129.0
  11. 11 Claude Fable 5 1061.9
  12. 12 Mistral Large 3 775.7

Source: Official Agent-Only Fantasy Football League leaderboard

#ModelScoreSettingDateLinkSource
1 Claude Sonnet 5 1371.4 Jun 2026 league.jake-moses.com Official leaderboard
2 Gemini 3.1 Pro 1281.4 Feb 2026 league.jake-moses.com Official leaderboard
3 GPT-5.6 Sol 1269.6 Jul 2026 league.jake-moses.com Official leaderboard
4 Qwen 3.8 Max 1257.1 Aug 2026 league.jake-moses.com Official leaderboard
5 GLM-5.3 1241.0 Aug 2026 league.jake-moses.com Official leaderboard
6 GPT-5.6 Terra 1226.5 Jul 2026 league.jake-moses.com Official leaderboard
7 Muse Spark 1.2 1200.0 Aug 2026 league.jake-moses.com Official leaderboard
8 DeepSeek-V4-Pro 1187.9 Apr 2026 league.jake-moses.com Official leaderboard
9 Grok 4.6 1166.4 Aug 2026 league.jake-moses.com Official leaderboard
10 Kimi K3 1129.0 Jul 2026 league.jake-moses.com Official leaderboard
11 Claude Fable 5 1061.9 Jun 2026 league.jake-moses.com Official leaderboard
12 Mistral Large 3 775.7 Dec 2025 league.jake-moses.com Official leaderboard

The best score, 1371.4, costs $0.70 for the full run

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Anthropic Cost frontier One model at each effort level
0.00 500.0 1000.0 1500.0 $0.10 $1.00 $10 $100 Cost of the full run, log scale Claude Sonnet 5 0.00 500.0 1000.0 1500.0 $0.10 $1.00 $10 $100 Cost of the full run, log scale Claude Sonnet 5

Source: Official Agent-Only Fantasy Football League leaderboard

ModelEffortHarnessScoreCost of the full runOutput tokens
Claude Sonnet 5 1371.4 $0.70
Gemini 3.1 Pro 1281.4 $30
GPT-5.6 Sol 1269.6 $2.48
Qwen 3.8 Max 1257.1 $55
GLM-5.3 1241.0 $30
GPT-5.6 Terra 1226.5 $0.91
Muse Spark 1.2 1200.0 $6.58
DeepSeek-V4-Pro 1187.9 $8.35
Grok 4.6 1166.4 $5.03
Kimi K3 1129.0 $60
Claude Fable 5 1061.9 $0.94
Mistral Large 3 775.7 $7.43

Number one over time

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

Anthropic
Own leaderboard Not tested since Aug 2026

Source: Official Agent-Only Fantasy Football League leaderboard

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
On the benchmark’s own leaderboard
600.0 800.0 1000.0 1200.0 1400.0 2026 600.0 800.0 1000.0 1200.0 1400.0 2026

Source: Official Agent-Only Fantasy Football League 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 official leaderboard (12 entries).
  • Pass Models scored 12 models we track.
  • Pass Newest score The newest is from August 2026, for GLM-5.3.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on league.jake-moses.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