Benchmark Almanac

The Aggregate Chart Recall

GPT-6.2 Astra 0.22 leads since November 2026
Not in model cards

Models estimate ten years of monthly Wikipedia pageviews from each article title alone. The scorer averages each article’s root mean squared error in log views.

The maker reports 18 models on the same 197 articles. A separate score measures how closely each prediction follows the rises and falls.

Released
November 2026
Kind
Trivia and open questions
Level
School
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Time series
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
18
Models scored on its own leaderboard

GPT-6.2 Astra leads with 0.22

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.

  1. 1 GPT-6.2 Astra provider default 0.22
  2. 2 GPT-6.2 Sol provider default 0.24
  3. 3 GPT-6.1 Terra provider default 0.27
  4. 4 Gemini 4 Carbon provider default 0.27
  5. 5 Gemini 3.8 Flash provider default 0.28
  6. 6 Claude Opus 5.5 provider default 0.29
  7. 7 Claude Fable 5.2 provider default 0.29
  8. 8 GLM-5.3-Flash provider default 0.41
  9. 9 Muse Spark 1.3 provider default 0.41
  10. 10 MiMo-V2.6 Pro provider default 0.43
  11. 11 DeepSeek V4.1 Flash 1017 provider default 0.53
  12. 12 Muse Ember provider default 0.53
  13. 13 Mistral Large 4 provider default 0.57
  14. 14 MiniMax-M3.1-Flash provider default 0.59
  15. 15 Claude Sonnet 5.5 provider default 0.67
  16. 16 Qwen3.8 Flash provider default 0.73
  17. 17 GPT-6 Luna provider default 0.81
  18. 18 Claude Haiku 5.5 provider default 0.93

Source: Official The Aggregate Chart Recall leaderboard

#ModelScoreSettingReleasedRun onSource
1 GPT-6.2 Astra 0.22 provider default Nov 2026 Nov 2026 Official leaderboard
2 GPT-6.2 Sol 0.24 provider default Nov 2026 Nov 2026 Official leaderboard
3 GPT-6.1 Terra 0.27 provider default Oct 2026 Nov 2026 Official leaderboard
4 Gemini 4 Carbon 0.27 provider default Oct 2026 Nov 2026 Official leaderboard
5 Gemini 3.8 Flash 0.28 provider default Sep 2026 Nov 2026 Official leaderboard
6 Claude Opus 5.5 0.29 provider default Sep 2026 Nov 2026 Official leaderboard
7 Claude Fable 5.2 0.29 provider default Nov 2026 Nov 2026 Official leaderboard
8 GLM-5.3-Flash 0.41 provider default Aug 2026 Nov 2026 Official leaderboard
9 Muse Spark 1.3 0.41 provider default Sep 2026 Nov 2026 Official leaderboard
10 MiMo-V2.6 Pro 0.43 provider default Sep 2026 Nov 2026 Official leaderboard
11 DeepSeek V4.1 Flash 1017 0.53 provider default Oct 2026 Nov 2026 Official leaderboard
12 Muse Ember 0.53 provider default Nov 2026 Nov 2026 Official leaderboard
13 Mistral Large 4 0.57 provider default Oct 2026 Nov 2026 Official leaderboard
14 MiniMax-M3.1-Flash 0.59 provider default Oct 2026 Nov 2026 Official leaderboard
15 Claude Sonnet 5.5 0.67 provider default Sep 2026 Nov 2026 Official leaderboard
16 Qwen3.8 Flash 0.73 provider default Aug 2026 Nov 2026 Official leaderboard
17 GPT-6 Luna 0.81 provider default Sep 2026 Nov 2026 Official leaderboard
18 Claude Haiku 5.5 0.93 provider default Oct 2026 Nov 2026 Official leaderboard

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

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

OpenAI
Own leaderboard 2 leaders

Source: Official The Aggregate Chart Recall 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
0.40 0.60 0.80 1.00 2027 0.40 0.60 0.80 1.00 2027

Source: Official The Aggregate Chart Recall 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (18 entries).
  • Pass Models scored 18 models we track.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 6 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on theaggregate.ai: 18 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