Benchmark Almanac

Biblically Informed Bot Learning Evaluation

Qwen3.5-4B 52.3% leads since February 2026
Not in model cards

Models answer four-option questions about all 66 books of the Protestant Bible, biblical people, places, and measurements. The maker reports accuracy.

The maker lists accuracy for 27 quantized models. NotebookLM generated many questions and answers that the maker did not manually review.

Made by
MushroomGecko
Released
April 2025
Kind
Trivia and open questions
Level
School
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
Anyone
Last model added
March 2026
Scores refreshed
November 20th, 2026
27
Entries on its own leaderboard, 18 models we track

Qwen3.5-4B leads with 52.3% among models released by March 2026 Qwen3.5-4B leads with 52.3% among models released by March 2026

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.

The newest model with a score here came out in March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Qwen3.5-4B Q4_K_M 52.3%
  2. 2 Granite 4.0 H Micro Q4_K_M 51.4%
  3. 3 qwen3-4b-instruct-2507 Q4_K_M 50.9%
  4. 4 Qwen3-4B Q4_K_M 50.4%
  5. 5 Granite 4.1 3B Q4_K_M 48.5%
  6. 6 Qwen2.5 3b Instruct Q4_K_M 47.9%
  7. 7 granite-4.0-micro Q4_K_M 47.1%
  8. 8 Ministral 3 3B Instruct Q4_K_M 43.6%
  9. 9 Gemma 3n E2B Q4_K_M 42.8%
  10. 10 Llama 3.2 3b Instruct Q4_K_M 41.7%
  11. 11 Gemma 3 4B Q4_K_M 41.5%
  12. 12 Qwen2.5 1.5b Instruct Q4_K_M 41%
  13. 13 Phi-4 Mini Q4_K_M 40.8%
  14. 14 Gemma 2 2B IT Q4_K_M 40.2%
  15. 15 Granite 3.2 2b Instruct Q4_K_M 40.2%
  16. 16 Granite-3.1-2B-Instruct Q4_K_M 40%
  17. 17 LFM2 2.6b Exp Q4_K_M 39.3%
  18. 18 Nemotron 3 Nano 4B Q4_K_M 38.3%
  19. 19 Qwen3-1.7B Q4_K_M 37%
  20. 20 Gemma 4 E2B Q4_K_M 36.6%
  21. 21 Qwen3.5-2B Q4_K_M 34.6%
  22. 22 SmolLM2 1.7B Instruct Q4_K_M 30.4%
  23. 23 InternLM2.5 1.8b Q4_K_M 28.7%
  24. 24 Gemma 3 1B Q4_K_M 28%
  25. 25 Llama 3.2 1b Instruct Q4_K_M 24.3%
  26. 26 Qwen3-0.6B Q4_K_M 24.2%
  27. 27 Granite-3.1-1B-A400M-Instruct Q4_K_M 22.2%

Source: Official Biblically Informed Bot Learning Evaluation leaderboard

#EntryScoreSettingDateSource
1 Qwen3.5-4B 52.3% Q4_K_M Feb 2026 Official leaderboard
2 Granite 4.0 H Micro 51.4% Q4_K_M Official leaderboard
3 qwen3-4b-instruct-2507 50.9% Q4_K_M Aug 2025 Official leaderboard
4 Qwen3-4B 50.4% Q4_K_M Apr 2025 Official leaderboard
5 Granite 4.1 3B 48.5% Q4_K_M Official leaderboard
6 Qwen2.5 3b Instruct 47.9% Q4_K_M Official leaderboard
7 granite-4.0-micro 47.1% Q4_K_M Oct 2025 Official leaderboard
8 Ministral 3 3B Instruct 43.6% Q4_K_M Dec 2025 Official leaderboard
9 Gemma 3n E2B 42.8% Q4_K_M Jun 2025 Official leaderboard
10 Llama 3.2 3b Instruct 41.7% Q4_K_M Official leaderboard
11 Gemma 3 4B 41.5% Q4_K_M Mar 2025 Official leaderboard
12 Qwen2.5 1.5b Instruct 41% Q4_K_M Official leaderboard
13 Phi-4 Mini 40.8% Q4_K_M Feb 2025 Official leaderboard
14 Gemma 2 2B IT 40.2% Q4_K_M Jul 2024 Official leaderboard
15 Granite 3.2 2b Instruct 40.2% Q4_K_M Official leaderboard
16 Granite-3.1-2B-Instruct 40% Q4_K_M Dec 2024 Official leaderboard
17 LFM2 2.6b Exp 39.3% Q4_K_M Official leaderboard
18 Nemotron 3 Nano 4B 38.3% Q4_K_M Mar 2026 Official leaderboard
19 Qwen3-1.7B 37% Q4_K_M Apr 2025 Official leaderboard
20 Gemma 4 E2B 36.6% Q4_K_M Mar 2026 Official leaderboard
21 Qwen3.5-2B 34.6% Q4_K_M Feb 2026 Official leaderboard
22 SmolLM2 1.7B Instruct 30.4% Q4_K_M Oct 2024 Official leaderboard
23 InternLM2.5 1.8b 28.7% Q4_K_M Official leaderboard
24 Gemma 3 1B 28% Q4_K_M Mar 2025 Official leaderboard
25 Llama 3.2 1b Instruct 24.3% Q4_K_M Official leaderboard
26 Qwen3-0.6B 24.2% Q4_K_M Apr 2025 Official leaderboard
27 Granite-3.1-1B-A400M-Instruct 22.2% Q4_K_M Dec 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen3.5-4B 52.3% Q4_K_M Feb 2026 Official leaderboard
2 qwen3-4b-instruct-2507 50.9% Q4_K_M Aug 2025 Official leaderboard
3 Qwen3-4B 50.4% Q4_K_M Apr 2025 Official leaderboard
4 granite-4.0-micro 47.1% Q4_K_M Oct 2025 Official leaderboard
5 Ministral 3 3B Instruct 43.6% Q4_K_M Dec 2025 Official leaderboard
6 Gemma 3n E2B 42.8% Q4_K_M Jun 2025 Official leaderboard
7 Gemma 3 4B 41.5% Q4_K_M Mar 2025 Official leaderboard
8 Phi-4 Mini 40.8% Q4_K_M Feb 2025 Official leaderboard
9 Gemma 2 2B IT 40.2% Q4_K_M Jul 2024 Official leaderboard
10 Granite-3.1-2B-Instruct 40% Q4_K_M Dec 2024 Official leaderboard
11 Nemotron 3 Nano 4B 38.3% Q4_K_M Mar 2026 Official leaderboard
12 Qwen3-1.7B 37% Q4_K_M Apr 2025 Official leaderboard
13 Gemma 4 E2B 36.6% Q4_K_M Mar 2026 Official leaderboard
14 Qwen3.5-2B 34.6% Q4_K_M Feb 2026 Official leaderboard
15 SmolLM2 1.7B Instruct 30.4% Q4_K_M Oct 2024 Official leaderboard
16 Gemma 3 1B 28% Q4_K_M Mar 2025 Official leaderboard
17 Qwen3-0.6B 24.2% Q4_K_M Apr 2025 Official leaderboard
18 Granite-3.1-1B-A400M-Instruct 22.2% Q4_K_M Dec 2024 Official leaderboard

4 models have held number one on the official leaderboard since its release in April 2025

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

Google DeepMind Qwen Other labs
Own leaderboard Not tested since Mar 2026
Qwen3.5-4B 52.3%

Source: Official Biblically Informed Bot Learning Evaluation 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% 2025 2026 Near the ceiling (85%) Qwen3.5-4B qwen3-4b-instruct-2507 Gemma 3 4B Gemma 2 2B IT 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Qwen3.5-4B Gemma 3 4B

Source: Official Biblically Informed Bot Learning Evaluation 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 8 months ago, in March 2026, for Gemma 4 E2B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (27 entries).
  • Pass Models scored 18 models we track, plus 9 other entries on its leaderboard.
  • Warning Newest score The newest came 8 months ago, in March 2026, for Gemma 4 E2B.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 52.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 18 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