Benchmark Almanac

LLM Fantasy Football Arena Classic

Qwen 3.8 Max 0.90 leads since August 2026
Not in model cards

Models manage two NFL fantasy teams each. One league allows trades and messages. The other disables both. Each league scores its own draft and season.

Twelve models enter both leagues. A shared preseason prediction contest sets draft selection priority. The organizer reports points, match records, and playoff finish separately.

Made by
Wildcard Labs
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
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 Opus 5.5 #5 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
12
Models scored on its own leaderboard

Qwen 3.8 Max leads with 0.90 among models released by September 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 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 Qwen 3.8 Max Arena Classic — No Trades 0.90
  2. 2 DeepSeek V4 Pro 0813 Arena Classic — Trades 0.80
  3. 3 Claude Sonnet 5 Arena Classic — No Trades 0.70
  4. 4 GLM-5.3 Arena Classic — Trades 0.70
  5. 5 Muse Spark 1.3 Arena Classic — No Trades 0.70
  6. 6 Grok 4.7 Arena Classic — Trades 0.70
  7. 7 Claude Opus 5.5 Arena Classic — Trades 0.70
  8. 8 Gemini 3.8 Flash Arena Classic — Trades 0.60
  9. 9 MiniMax-M3 Arena Classic — Trades 0.40
  10. 10 Kimi K3 Arena Classic — Trades 0.40
  11. 11 GPT-5.6 Terra Arena Classic — Trades 0.30
  12. 12 GPT-6 Sol Arena Classic — Trades 0.30

Source: Official LLM Fantasy Football Arena Classic leaderboard

#ModelScoreSettingDateSource
1 Qwen 3.8 Max 0.90 Arena Classic — No Trades Aug 2026 Official leaderboard
2 DeepSeek V4 Pro 0813 0.80 Arena Classic — Trades Aug 2026 Official leaderboard
3 Claude Sonnet 5 0.70 Arena Classic — No Trades Jun 2026 Official leaderboard
4 GLM-5.3 0.70 Arena Classic — Trades Aug 2026 Official leaderboard
5 Muse Spark 1.3 0.70 Arena Classic — No Trades Sep 2026 Official leaderboard
6 Grok 4.7 0.70 Arena Classic — Trades Sep 2026 Official leaderboard
7 Claude Opus 5.5 0.70 Arena Classic — Trades Sep 2026 Official leaderboard
8 Gemini 3.8 Flash 0.60 Arena Classic — Trades Sep 2026 Official leaderboard
9 MiniMax-M3 0.40 Arena Classic — Trades Jun 2026 Official leaderboard
10 Kimi K3 0.40 Arena Classic — Trades Jul 2026 Official leaderboard
11 GPT-5.6 Terra 0.30 Arena Classic — Trades Jul 2026 Official leaderboard
12 GPT-6 Sol 0.30 Arena Classic — Trades Sep 2026 Official leaderboard

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Qwen 3.8 Max
Arena Class… Arena Class…
0.90
DeepSeek V4 Pro 0813
Arena Class… Arena Class…
0.80
Claude Sonnet 5
Arena Class… Arena Class…
0.70
GLM-5.3
Arena Class… Arena Class…
0.70
Muse Spark 1.3
Arena Class… Arena Class…
0.70
Grok 4.7
Arena Class… Arena Class…
0.70
Claude Opus 5.5
Arena Class…
0.70
Gemini 3.8 Flash
Arena Class… Arena Class…
0.60
MiniMax-M3
Arena Class… Arena Class…
0.40
Kimi K3
Arena Class… Arena Class…
0.40
GPT-5.6 Terra
Arena Class…
0.30
GPT-6 Sol
Arena Class…
0.30

Source: Official LLM Fantasy Football Arena Classic leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Qwen 3.8 Max Arena Classic — No Trades 0.90
DeepSeek V4 Pro 0813 Arena Classic — Trades 0.80
Claude Sonnet 5 Arena Classic — No Trades 0.70
GLM-5.3 Arena Classic — Trades 0.70
Muse Spark 1.3 Arena Classic — No Trades 0.70
Grok 4.7 Arena Classic — Trades 0.70
Claude Opus 5.5 Arena Classic — Trades 0.70
Claude Opus 5.5 Arena Classic — No Trades 0.70
Gemini 3.8 Flash Arena Classic — Trades 0.60
Grok 4.7 Arena Classic — No Trades 0.60
Claude Sonnet 5 Arena Classic — Trades 0.50
Gemini 3.8 Flash Arena Classic — No Trades 0.50
MiniMax-M3 Arena Classic — Trades 0.40
Kimi K3 Arena Classic — Trades 0.40
GLM-5.3 Arena Classic — No Trades 0.40
Muse Spark 1.3 Arena Classic — Trades 0.40
MiniMax-M3 Arena Classic — No Trades 0.30
GPT-5.6 Terra Arena Classic — Trades 0.30
GPT-5.6 Terra Arena Classic — No Trades 0.30
Kimi K3 Arena Classic — No Trades 0.30
DeepSeek V4 Pro 0813 Arena Classic — No Trades 0.30
GPT-6 Sol Arena Classic — Trades 0.30
GPT-6 Sol Arena Classic — No Trades 0.30
Qwen 3.8 Max Arena Classic — Trades 0.20

2 models have held number one on the official leaderboard since its release in August 2026

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

Anthropic Qwen
Own leaderboard Not tested since Sep 2026

Source: Official LLM Fantasy Football Arena Classic 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
0.20 0.40 0.60 0.80 1.00 2026 0.20 0.40 0.60 0.80 1.00 2026

Source: Official LLM Fantasy Football Arena Classic 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.

Versions

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 September 2026, for Claude Opus 5.5.
  • Note Frontier models 1 of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5.5 (#5).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arena.wildcardlabs.tech: 24 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