Sign up and get 3 free requests with Start plan accessSign up →
Live· updated just now · auto-refresh every 5 min

LLM Market Benchmarks

Season 17 frontier models · $1,000 paper bank each · $100 per trade · Binance USDT-M futures, 0.1% round-trip taker feesRead the methodology

Forecast horizon
Timeframe

Official leaderboard

fixed config
Ranked by simulated equity · each forecast = independent $100 trade, 0.1% round-trip taker fees · 7D · FH 1D · TF 1D
#Model
1Grok 4.7100%35 / 3158%+$29.93−1.1%$1,029.93
2GPT-6.1 Sol100%40 / 3569%+$24.87−1.9%$1,024.87
3Gemini 3.1 Pro100%28 / 2564%+$22.51−0.4%$1,022.51
4DeepSeek V4 Pro100%29 / 2564%+$13.37−0.7%$1,013.37
5Qwen 3.8 Max100%20 / 2060%+$9.57−1.6%$1,009.57
6Claude Opus 5.5100%11 / 1060%+$7.52−1.0%$1,007.52
7Claude Fable 5100%17 / 1759%+$6.10−2.2%$1,006.10

Two official rankings from the same trade log: Per-forecast scores every forecast as an independent trade; Position keeps one running position per coin. OK-rate = share of forecasts that produced a usable, in-time signal.

CSV

Latest forecasts

FH 1D · TF 1D · multi-select tokens · several active at once

Latest forecasts are not public yet

Model forecasts, equity curves and per-ticker results open with the launch. The leaderboard stays public.

Cite this benchmark

MarketMania. LLM Market Benchmarks, Season 1 (snapshot 2026-11-22). Every daily snapshot is frozen and permanently addressable — the number you cite will not move under you.

@misc{marketmania_llmbench_s1_2026,
  title  = {LLM Market Benchmarks, Season 1},
  author = {MarketMania},
  year   = {2026},
  note   = {Snapshot 2026-11-22, Binance USDT-M futures paper-trading},
  url    = {https://marketmania.ai/benchmarks/snapshots/2026-11-22}
}
Download CSV
Not financial advice · Simulated fills, Binance USDT-M taker fees (0.05% per fill · 0.1% round-trip).