Benchmark Almanac

TIME (time series forecasting)

TimeRSI-1.5 0.61 tops its leaderboard
Not in model cards

Models forecast time series over short, medium, and long horizons without training on the target task.

The board reports mean absolute scaled error and probabilistic forecast scores by dataset and temporal pattern.

Made by
Real-TSF
Released
February 2026
Kind
Real-world events
Level
University
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Subject
Mathematics
In and out
Time series → Time series
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
48
Entries on its own leaderboard, 0 models we track

TimeRSI-1.5 tops the leaderboard with 0.61

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 TimeRSI-1.5 0.61
  2. 2 PDM-Nano 0.63
  3. 3 Timestral-209M 0.63
  4. 4 Timestral-123M 0.63
  5. 5 TimeRSI 0.63
  6. 6 PDM-Pico 0.63
  7. 7 ci-proto 0.63
  8. 8 Simons-297M 0.64
  9. 9 t0_gamma 0.64
  10. 10 QiYao-M 0.64
  11. 11 Timestral-28M 0.64
  12. 12 ChakraTS 0.64
  13. 13 Simons-178M 0.64
  14. 14 TimesFM-3 0.64
  15. 15 Toto-2.0-2.5B 0.64
  16. 16 Simons-60M 0.64
  17. 17 Toto-2.0-313m 0.64
  18. 18 Toto-2.0-1B 0.65
  19. 19 PDM-Femto 0.65
  20. 20 Simons-25M 0.65
  21. 21 Timestral-5M 0.65
  22. 22 Chronos-2 0.66
  23. 23 PatchTST-FM-Extended 0.66
  24. 24 t0_beta 0.67
  25. 25 Hart-36M 0.67
  26. 26 Tabby 0.67
  27. 27 OmniScient 0.67
  28. 28 TimesFM-2.5 0.67
  29. 29 Toto-2.0-22m 0.67
  30. 30 PatchTST-FM-R1 0.67
  31. 31 Tabby-Pretrain 0.68
  32. 32 TiRex 0.68
  33. 33 Toto-2.0-4m 0.69
  34. 34 TS-ICL 0.69
  35. 35 Toto 0.70
  36. 36 Eidos 0.70
  37. 37 Timer-S1 0.70
  38. 38 Moirai2 0.70
  39. 39 TimesFM-2.0 0.72
  40. 40 Chronos-bolt 0.73
  41. 41 Kairos 0.74
  42. 42 sundial_base 0.76
  43. 43 Fracast-0 0.77
  44. 44 litespecformer 0.79
  45. 45 TimesFM-1.0 0.79
  46. 46 visiontspp_base 0.81
  47. 47 Moirai_base 0.83
  48. 48 seasonal_naive 1.00

Source: Official TIME (time series forecasting) leaderboard

#EntryScoreSettingDateSource
1 TimeRSI-1.5 0.61 Official leaderboard
2 PDM-Nano 0.63 Official leaderboard
3 Timestral-209M 0.63 Official leaderboard
4 Timestral-123M 0.63 Official leaderboard
5 TimeRSI 0.63 Official leaderboard
6 PDM-Pico 0.63 Official leaderboard
7 ci-proto 0.63 Official leaderboard
8 Simons-297M 0.64 Official leaderboard
9 t0_gamma 0.64 Official leaderboard
10 QiYao-M 0.64 Official leaderboard
11 Timestral-28M 0.64 Official leaderboard
12 ChakraTS 0.64 Official leaderboard
13 Simons-178M 0.64 Official leaderboard
14 TimesFM-3 0.64 Official leaderboard
15 Toto-2.0-2.5B 0.64 Official leaderboard
16 Simons-60M 0.64 Official leaderboard
17 Toto-2.0-313m 0.64 Official leaderboard
18 Toto-2.0-1B 0.65 Official leaderboard
19 PDM-Femto 0.65 Official leaderboard
20 Simons-25M 0.65 Official leaderboard
21 Timestral-5M 0.65 Official leaderboard
22 Chronos-2 0.66 Official leaderboard
23 PatchTST-FM-Extended 0.66 Official leaderboard
24 t0_beta 0.67 Official leaderboard
25 Hart-36M 0.67 Official leaderboard
26 Tabby 0.67 Official leaderboard
27 OmniScient 0.67 Official leaderboard
28 TimesFM-2.5 0.67 Official leaderboard
29 Toto-2.0-22m 0.67 Official leaderboard
30 PatchTST-FM-R1 0.67 Official leaderboard
31 Tabby-Pretrain 0.68 Official leaderboard
32 TiRex 0.68 Official leaderboard
33 Toto-2.0-4m 0.69 Official leaderboard
34 TS-ICL 0.69 Official leaderboard
35 Toto 0.70 Official leaderboard
36 Eidos 0.70 Official leaderboard
37 Timer-S1 0.70 Official leaderboard
38 Moirai2 0.70 Official leaderboard
39 TimesFM-2.0 0.72 Official leaderboard
40 Chronos-bolt 0.73 Official leaderboard
41 Kairos 0.74 Official leaderboard
42 sundial_base 0.76 Official leaderboard
43 Fracast-0 0.77 Official leaderboard
44 litespecformer 0.79 Official leaderboard
45 TimesFM-1.0 0.79 Official leaderboard
46 visiontspp_base 0.81 Official leaderboard
47 Moirai_base 0.83 Official leaderboard
48 seasonal_naive 1.00 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 (48 entries).
  • Pass Models scored 48 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 huggingface.co: 48 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