Benchmark Almanac

The Aggregate Day-one Recall Check

Claude Fable 5 61.8% leads since August 2026
Not in model cards

Models answer 34 questions about 12 public-domain books from memory. The scorer matches answers against a key and excludes empty replies.

The maker ranks 45 models. This short form omits the longer book test’s second review. Six models answered fewer than 34 questions.

Released
August 2026
Kind
Trivia and open questions
Level
School
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
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
45
Entries on its own leaderboard, 36 models we track

2 models share the top score of 61.8% 2 models share the top score of 61.8%

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. This view shows only models we track, each at its best.

  1. 1 Claude Fable 5 unrecorded 61.8%
  2. 2 Claude Fable 5.2 high 61.8%
  3. 3 Claude Opus 5 unrecorded 58.8%
  4. 4 Claude Fable 5.1 unrecorded 55.9%
  5. 5 GPT-6.2 Astra high 48.5%
  6. 6 GPT-5.5 unrecorded 47.1%
  7. 7 GPT-6.2 Sol high 44.1%
  8. 8 Claude Opus 4.8 unrecorded 41.2%
  9. 9 Particle-1 free route, unrecorded 38.2%
  10. 10 GPT-5.2 unrecorded 38.2%
  11. 11 GPT-5.4 unrecorded 38.2%
  12. 12 Nex N2.5 Mini free route, unrecorded 32.4%
  13. 13 Kimi K2.6 unrecorded 32.4%
  14. 14 DeepSeek-V4-Pro unrecorded 32.4%
  15. 15 Nemotron 3 Ultra free route, unrecorded 32.3%
  16. 16 Nex N2.5 Pro free route, unrecorded 29.4%
  17. 17 GPT-5.4 Mini unrecorded 29.4%
  18. 18 Qwen 3.6 35B-A3B unrecorded 29.4%
  19. 19 Nemotron 3.5 Super VL free route, unrecorded 29.4%
  20. 20 Mistral Large 4 Mistral API, unrecorded 27.3%
  21. 21 ERNIE 5.5 Flash Preview free route, unrecorded 26.5%
  22. 22 Nemotron 3 Super free route, unrecorded 26.5%
  23. 23 Kimi K2 Sep 2025, unrecorded 23.5%
  24. 24 Qwen 3.6 Plus unrecorded 23.5%
  25. 25 Ling-3.0-flash-Fin free route, unrecorded 23.5%
  26. 26 DeepSeek V4.1 Flash 1017 Mistral API, unrecorded 23.5%
  27. 27 gpt-oss-120b unrecorded 20.6%
  28. 28 Ling-3.2-flash free route, unrecorded 17.6%
  29. 29 Apodex 1.1 Mini free route, unrecorded 17.6%
  30. 30 Ling-3.0-flash-sante free route, unrecorded 17.6%
  31. 31 Ling-3.0-flash-VL free route, unrecorded 17.6%
  32. 32 Nemotron 3.5 Lightning 30B-A3B free route, unrecorded 17.6%
  33. 33 Space Bunny Alpha stealth release, unrecorded 14.7%
  34. 34 Gemma 4 26B A4B free route, unrecorded 14.7%
  35. 35 Gemma 4 31B IT free route, unrecorded 14.7%
  36. 36 Ling-3.1-flash unrecorded 14.7%
  37. 37 MiniMax-M3.1-Flash free route, unrecorded 14.7%
  38. 38 Dots3-Note (Preview) free route, unrecorded 11.8%
  39. 39 Claude Haiku 4.5 unrecorded 8.80%
  40. 40 North Mini Code 1.0 free route, unrecorded 8.80%
  41. 41 Laguna XS 2.1 free route, unrecorded 8.80%
  42. 42 Flint free route, unrecorded 6.20%
  43. 43 Laguna S 2.1 free route, unrecorded 6.20%
  44. 44 LFM3-1.7B free route, unrecorded 3.10%
  45. 45 LFM2.5-2.6B free route, unrecorded 2.90%

Source: Official The Aggregate Day-one Recall Check leaderboard

Source: Official The Aggregate Day-one Recall Check leaderboard

#EntryScoreSettingDateSource
1 Claude Fable 5 61.8% unrecorded Jun 2026 Official leaderboard
2 Claude Fable 5.2 61.8% high Nov 2026 Official leaderboard
3 Claude Opus 5 58.8% unrecorded Jul 2026 Official leaderboard
4 Claude Fable 5.1 55.9% unrecorded Sep 2026 Official leaderboard
5 GPT-6.2 Astra 48.5% high Nov 2026 Official leaderboard
6 GPT-5.5 47.1% unrecorded Apr 2026 Official leaderboard
7 GPT-6.2 Sol 44.1% high Nov 2026 Official leaderboard
8 Claude Opus 4.8 41.2% unrecorded May 2026 Official leaderboard
9 Particle-1 38.2% free route, unrecorded Official leaderboard
10 GPT-5.2 38.2% unrecorded Dec 2025 Official leaderboard
11 GPT-5.4 38.2% unrecorded Mar 2026 Official leaderboard
12 Nex N2.5 Mini 32.4% free route, unrecorded Official leaderboard
13 Kimi K2.6 32.4% unrecorded Apr 2026 Official leaderboard
14 DeepSeek-V4-Pro 32.4% unrecorded Apr 2026 Official leaderboard
15 Nemotron 3 Ultra 32.3% free route, unrecorded Jun 2026 Official leaderboard
16 Nex N2.5 Pro 29.4% free route, unrecorded Official leaderboard
17 GPT-5.4 Mini 29.4% unrecorded Mar 2026 Official leaderboard
18 Qwen 3.6 35B-A3B 29.4% unrecorded Apr 2026 Official leaderboard
19 Nemotron 3.5 Super VL 29.4% free route, unrecorded Oct 2026 Official leaderboard
20 Mistral Large 4 27.3% Mistral API, unrecorded Oct 2026 Official leaderboard
21 ERNIE 5.5 Flash Preview 26.5% free route, unrecorded Official leaderboard
22 Nemotron 3 Super 26.5% free route, unrecorded Mar 2026 Official leaderboard
23 Kimi K2 Sep 2025 23.5% unrecorded Sep 2025 Official leaderboard
24 Qwen 3.6 Plus 23.5% unrecorded Mar 2026 Official leaderboard
25 Ling-3.0-flash-Fin 23.5% free route, unrecorded Sep 2026 Official leaderboard
26 DeepSeek V4.1 Flash 1017 23.5% Mistral API, unrecorded Oct 2026 Official leaderboard
27 gpt-oss-120b 20.6% unrecorded Aug 2025 Official leaderboard
28 Ling-3.2-flash 17.6% free route, unrecorded Official leaderboard
29 Apodex 1.1 Mini 17.6% free route, unrecorded Official leaderboard
30 Ling-3.0-flash-sante 17.6% free route, unrecorded Official leaderboard
31 Ling-3.0-flash-VL 17.6% free route, unrecorded Official leaderboard
32 Nemotron 3.5 Lightning 30B-A3B 17.6% free route, unrecorded Aug 2026 Official leaderboard
33 Space Bunny Alpha 14.7% stealth release, unrecorded Official leaderboard
34 Gemma 4 26B A4B 14.7% free route, unrecorded Apr 2026 Official leaderboard
35 Gemma 4 31B IT 14.7% free route, unrecorded Apr 2026 Official leaderboard
36 Ling-3.1-flash 14.7% unrecorded Oct 2026 Official leaderboard
37 MiniMax-M3.1-Flash 14.7% free route, unrecorded Oct 2026 Official leaderboard
38 Dots3-Note (Preview) 11.8% free route, unrecorded Official leaderboard
39 Claude Haiku 4.5 8.80% unrecorded Oct 2025 Official leaderboard
40 North Mini Code 1.0 8.80% free route, unrecorded Jun 2026 Official leaderboard
41 Laguna XS 2.1 8.80% free route, unrecorded Jul 2026 Official leaderboard
42 Flint 6.20% free route, unrecorded Official leaderboard
43 Laguna S 2.1 6.20% free route, unrecorded Jul 2026 Official leaderboard
44 LFM3-1.7B 3.10% free route, unrecorded Oct 2026 Official leaderboard
45 LFM2.5-2.6B 2.90% free route, unrecorded Aug 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5 61.8% unrecorded Jun 2026 Official leaderboard
2 Claude Fable 5.2 61.8% high Nov 2026 Official leaderboard
3 Claude Opus 5 58.8% unrecorded Jul 2026 Official leaderboard
4 Claude Fable 5.1 55.9% unrecorded Sep 2026 Official leaderboard
5 GPT-6.2 Astra 48.5% high Nov 2026 Official leaderboard
6 GPT-5.5 47.1% unrecorded Apr 2026 Official leaderboard
7 GPT-6.2 Sol 44.1% high Nov 2026 Official leaderboard
8 Claude Opus 4.8 41.2% unrecorded May 2026 Official leaderboard
9 GPT-5.2 38.2% unrecorded Dec 2025 Official leaderboard
10 GPT-5.4 38.2% unrecorded Mar 2026 Official leaderboard
11 Kimi K2.6 32.4% unrecorded Apr 2026 Official leaderboard
12 DeepSeek-V4-Pro 32.4% unrecorded Apr 2026 Official leaderboard
13 Nemotron 3 Ultra 32.3% free route, unrecorded Jun 2026 Official leaderboard
14 GPT-5.4 Mini 29.4% unrecorded Mar 2026 Official leaderboard
15 Qwen 3.6 35B-A3B 29.4% unrecorded Apr 2026 Official leaderboard
16 Nemotron 3.5 Super VL 29.4% free route, unrecorded Oct 2026 Official leaderboard
17 Mistral Large 4 27.3% Mistral API, unrecorded Oct 2026 Official leaderboard
18 Nemotron 3 Super 26.5% free route, unrecorded Mar 2026 Official leaderboard
19 Kimi K2 Sep 2025 23.5% unrecorded Sep 2025 Official leaderboard
20 Qwen 3.6 Plus 23.5% unrecorded Mar 2026 Official leaderboard
21 Ling-3.0-flash-Fin 23.5% free route, unrecorded Sep 2026 Official leaderboard
22 DeepSeek V4.1 Flash 1017 23.5% Mistral API, unrecorded Oct 2026 Official leaderboard
23 gpt-oss-120b 20.6% unrecorded Aug 2025 Official leaderboard
24 Ling-3.2-flash 17.6% free route, unrecorded Official leaderboard
25 Nemotron 3.5 Lightning 30B-A3B 17.6% free route, unrecorded Aug 2026 Official leaderboard
26 Gemma 4 26B A4B 14.7% free route, unrecorded Apr 2026 Official leaderboard
27 Gemma 4 31B IT 14.7% free route, unrecorded Apr 2026 Official leaderboard
28 Ling-3.1-flash 14.7% unrecorded Oct 2026 Official leaderboard
29 MiniMax-M3.1-Flash 14.7% free route, unrecorded Oct 2026 Official leaderboard
30 Claude Haiku 4.5 8.80% unrecorded Oct 2025 Official leaderboard
31 North Mini Code 1.0 8.80% free route, unrecorded Jun 2026 Official leaderboard
32 Laguna XS 2.1 8.80% free route, unrecorded Jul 2026 Official leaderboard
33 Flint 6.20% free route, unrecorded Official leaderboard
34 Laguna S 2.1 6.20% free route, unrecorded Jul 2026 Official leaderboard
35 LFM3-1.7B 3.10% free route, unrecorded Oct 2026 Official leaderboard
36 LFM2.5-2.6B 2.90% free route, unrecorded Aug 2026 Official leaderboard

Number one over time

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

Anthropic
Own leaderboard 1 leader

Source: Official The Aggregate Day-one Recall Check 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 GPT-5.5 GPT-5.2 Kimi K2 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5 GPT-5.5

Source: Official The Aggregate Day-one Recall Check 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 (45 entries).
  • Pass Models scored 36 models we track, plus 9 other entries on its leaderboard.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 3 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 61.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on theaggregate.ai: 36 rows for models we track and 9 other entries 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