Benchmark Almanac

The Aggregate Exotic Fact Recall

Claude Fable 5.2 75% leads since November 2026
Not in model cards

Models recall exact fields from five public registries without looking them up. The bank mixes familiar entries with randomly sampled obscure ones.

The maker ranks 15 models. Fourteen answered all 85 questions, and one answered 84. The original set includes 49 obscure entries.

Released
September 2026
Kind
Trivia and open questions
Level
Expert
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
15
Models scored on its own leaderboard

Claude Fable 5.2 leads with 75%

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 Claude Fable 5.2 high 75%
  2. 2 GPT-5.6 Sol high 63.5%
  3. 3 Claude Fable 5.1 high 62.4%
  4. 4 Claude Fable 5 high 61.2%
  5. 5 GPT-6.2 Astra high 60%
  6. 6 GPT-6 Astra high 56.5%
  7. 7 Gemini 3.7 Flash high 55.3%
  8. 8 GPT-6.2 Sol high 51.8%
  9. 9 Claude Opus 5 high 50.6%
  10. 10 DeepSeek-V4-Pro high 49.4%
  11. 11 GPT-5.4 high 41.2%
  12. 12 GPT-5.4 Mini high 36.5%
  13. 13 Qwen 3.6 Plus high 31.8%
  14. 14 Qwen 3.6 35B-A3B high 27.1%
  15. 15 Claude Haiku 4.5 high 23.5%

Source: Official The Aggregate Exotic Fact Recall leaderboard

#ModelScoreSettingReleasedRun onSource
1 Claude Fable 5.2 75% high Nov 2026 Nov 2026 Official leaderboard
2 GPT-5.6 Sol 63.5% high Jul 2026 Nov 2026 Official leaderboard
3 Claude Fable 5.1 62.4% high Sep 2026 Nov 2026 Official leaderboard
4 Claude Fable 5 61.2% high Jun 2026 Nov 2026 Official leaderboard
5 GPT-6.2 Astra 60% high Nov 2026 Nov 2026 Official leaderboard
6 GPT-6 Astra 56.5% high Sep 2026 Nov 2026 Official leaderboard
7 Gemini 3.7 Flash 55.3% high Aug 2026 Nov 2026 Official leaderboard
8 GPT-6.2 Sol 51.8% high Nov 2026 Nov 2026 Official leaderboard
9 Claude Opus 5 50.6% high Jul 2026 Nov 2026 Official leaderboard
10 DeepSeek-V4-Pro 49.4% high Apr 2026 Nov 2026 Official leaderboard
11 GPT-5.4 41.2% high Mar 2026 Nov 2026 Official leaderboard
12 GPT-5.4 Mini 36.5% high Mar 2026 Nov 2026 Official leaderboard
13 Qwen 3.6 Plus 31.8% high Mar 2026 Nov 2026 Official leaderboard
14 Qwen 3.6 35B-A3B 27.1% high Apr 2026 Nov 2026 Official leaderboard
15 Claude Haiku 4.5 23.5% high Oct 2025 Nov 2026 Official leaderboard

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

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

OpenAI Anthropic
Own leaderboard 2 leaders

Source: Official The Aggregate Exotic Fact 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 Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 GPT-5.6 Sol DeepSeek-V4-Pro GPT-5.4 Claude Haiku 4.5 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 GPT-5.6 Sol

Source: Official The Aggregate Exotic Fact 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

10 of 11 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (15 entries).
  • Pass Models scored 15 models we track.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 4 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 75%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on theaggregate.ai: 15 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