Benchmark Almanac

CREF

Toto 2 (1B) 35.5% tops its leaderboard
Not in model cards

Models submit forecasts before the target period begins and receive scores after the actual values become available.

CREF compares errors against a seasonal baseline and weights each task equally. The November 2026 public snapshot covers forecasts dating to April.

Made by
Andreas Auer and colleagues
Released
November 2026
Kind
Real-world events
Level
University
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Time series → Text
Interaction
Single turn
Items from
Live play or votes
Refresh
Live
Run by
A host
In views
Kept fresh
26
Entries on its own leaderboard, 0 models we track

Toto 2 (1B) tops the leaderboard with 35.5%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 Toto 2 (1B) 35.5%
  2. 2 Chronos 2 35.3%
  3. 3 TimesFM 2.5 35.2%
  4. 4 FlowState r1.1 35.2%
  5. 5 TiRex 33.1%
  6. 6 TabPFN-TS 3 31.9%
  7. 7 TiRex 2 31.7%
  8. 8 DP + Chronos2 (Sonnet 4.6) 31.6%
  9. 9 Moirai 2 30.4%
  10. 10 Direct Prompt (Opus 4.6) 29%
  11. 11 Chronos Bolt 28.8%
  12. 12 Agentic (Opus 4.x) 27.9%
  13. 13 Direct Prompt (Sonnet 4.6) 26.3%
  14. 14 DP + Chronos2 (GPT-5.6 Sol) 26.2%
  15. 15 TimesFM 3 26%
  16. 16 DP + Chronos2 (Opus 5) 24.8%
  17. 17 Direct Prompt (Opus 5) 23.7%
  18. 18 Agentic (Opus 5) 23.3%
  19. 19 t0-gamma 23.1%
  20. 20 Direct Prompt (GPT-5.6 Sol) 23.1%
  21. 21 Direct Prompt (Opus 4.8) 17.9%
  22. 22 Direct Prompt (Sonnet 5) 12.6%
  23. 23 AutoTheta 7.34%
  24. 24 Seasonal naive 0%
  25. 25 AutoETS -6.98%
  26. 26 Naive -23.07%

Source: Official CREF leaderboard

#EntryScoreSettingDateLinkSource
1 Toto 2 (1B) 35.5% Nov 2026 huggingface.co Official leaderboard
2 Chronos 2 35.3% Nov 2026 huggingface.co Official leaderboard
3 TimesFM 2.5 35.2% Nov 2026 huggingface.co Official leaderboard
4 FlowState r1.1 35.2% Nov 2026 huggingface.co Official leaderboard
5 TiRex 33.1% Nov 2026 huggingface.co Official leaderboard
6 TabPFN-TS 3 31.9% Nov 2026 huggingface.co Official leaderboard
7 TiRex 2 31.7% Nov 2026 huggingface.co Official leaderboard
8 DP + Chronos2 (Sonnet 4.6) 31.6% Nov 2026 Official leaderboard
9 Moirai 2 30.4% Nov 2026 huggingface.co Official leaderboard
10 Direct Prompt (Opus 4.6) 29% Nov 2026 Official leaderboard
11 Chronos Bolt 28.8% Nov 2026 huggingface.co Official leaderboard
12 Agentic (Opus 4.x) 27.9% Nov 2026 Official leaderboard
13 Direct Prompt (Sonnet 4.6) 26.3% Nov 2026 Official leaderboard
14 DP + Chronos2 (GPT-5.6 Sol) 26.2% Nov 2026 Official leaderboard
15 TimesFM 3 26% Nov 2026 huggingface.co Official leaderboard
16 DP + Chronos2 (Opus 5) 24.8% Nov 2026 Official leaderboard
17 Direct Prompt (Opus 5) 23.7% Nov 2026 Official leaderboard
18 Agentic (Opus 5) 23.3% Nov 2026 Official leaderboard
19 t0-gamma 23.1% Nov 2026 huggingface.co Official leaderboard
20 Direct Prompt (GPT-5.6 Sol) 23.1% Nov 2026 Official leaderboard
21 Direct Prompt (Opus 4.8) 17.9% Nov 2026 Official leaderboard
22 Direct Prompt (Sonnet 5) 12.6% Nov 2026 Official leaderboard
23 AutoTheta 7.34% Nov 2026 Official leaderboard
24 Seasonal naive 0% Nov 2026 Official leaderboard
25 AutoETS -6.98% Nov 2026 Official leaderboard
26 Naive -23.07% Nov 2026 Official 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 Forecasting

All 47 in Forecasting
  • ForecastBench In use Models give probabilities for 500 auto-generated questions per round about future events, drawn from prediction markets and time-series datasets. Forecasts are scored with difficulty-adjusted Brier scores once the questions resolve. GPT-5.5 0.11
  • Prophet Arena In use Models and agents forecast open Kalshi prediction-market events and are scored once the events resolve. The live board ranks a difficulty-adjusted Arena score and also reports calibration error and market return. Claude Opus 5.5 86.2
  • Guesswork (The Aggregate) Not in model cards Models predict benchmark scores before publication. The maker ranks forecasts by mean absolute error after scaling each error by the variation in that benchmark’s scores. GPT-6 Astra 0.56
  • AGI-Pilled Bench Not in model cards Models forecast when AI will reach milestones that already happened in 2026. The score is the median years after 2026 across the forecast tasks. Claude Fable 5.2 6.50
  • Dutch Book Bench Not in model cards Models assign probabilities to related events in separate conversations. The grader checks whether inconsistent probabilities let a bettor guarantee a profit. Gemini 3.8 Flash 89.2%
  • Echo General AI Prediction Leaderboard Not in model cards Models forecast unresolved events drawn from prediction markets, synthesized news questions and expert-written questions. Forecasts made at aligned times are compared in pairwise battles, and an Elo fit ranks the models. DeepSeek-V4-Pro 1,018

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 (26 entries).
  • Pass Models scored 26 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on autogluon-fev-bench.hf.space: 26 entries at the last read, none a model we track.
  • 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