Benchmark Almanac

NeuroscienceBench

Claude Fable 5.2 41% leads since November 2026
Not in model cards

Agents analyze neuroscience research data and report a scientific conclusion. The score counts correct conclusions among graded runs.

LatchBio lists the evaluation in its V1 inventory.

Made by
LatchBio
Kind
Research science
Level
Expert
Scored
Checked automatically
Answers
Agent task
Measures
Capability
Language
English
Interaction
Agentic
Environment
Terminal
Items from
Real work and use
Run by
A host
Strongest model tested
Claude Fable 5.2 #2 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
22
Models scored on its own leaderboard

Claude Fable 5.2 leads with 41%

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 LSVP 41%
  2. 2 Claude Opus 5.5 LSVP 32.2%
  3. 3 Claude Opus 5 LSVP 30.8%
  4. 4 Claude Sonnet 5.5 LSVP 29.7%
  5. 5 Claude Fable 5.1 LSVP 28.4%
  6. 6 Grok 4.7 27.5%
  7. 7 GPT-6 Astra 22.7%
  8. 8 GPT-6.1 Terra 22.3%
  9. 9 GPT-6.1 Sol 22%
  10. 10 DeepSeek V4.1 Flash 22%
  11. 11 GPT-6 Luna 21.5%
  12. 12 Grok 4.6 21.3%
  13. 13 Claude Sonnet 5 LSVP 19.4%
  14. 14 Mistral Large 4 19.4%
  15. 15 Gemini 4 Argon 19.1%
  16. 16 Kimi K3 16.5%
  17. 17 GLM-5.3 16.5%
  18. 18 GPT-5.6 Sol 15.8%
  19. 19 Gemini 3.8 Flash 15.8%
  20. 20 GPT-5.6 Luna 15%
  21. 21 Nemotron 3 Ultra 12.1%
  22. 22 Nemotron 3.5 Lightning 30B-A3B 7.69%

Source: Official NeuroscienceBench leaderboard

#ModelScoreSettingDateSource
1 Claude Fable 5.2 41% LSVP, Claude Code Nov 2026 Official leaderboard
2 Claude Opus 5.5 32.2% LSVP, Pi Sep 2026 Official leaderboard
3 Claude Opus 5 30.8% LSVP, Pi Jul 2026 Official leaderboard
4 Claude Sonnet 5.5 29.7% LSVP, Claude Code Sep 2026 Official leaderboard
5 Claude Fable 5.1 28.4% LSVP, Pi Sep 2026 Official leaderboard
6 Grok 4.7 27.5% Grok Build Sep 2026 Official leaderboard
7 GPT-6 Astra 22.7% Pi Sep 2026 Official leaderboard
8 GPT-6.1 Terra 22.3% Pi Oct 2026 Official leaderboard
9 GPT-6.1 Sol 22% Pi Sep 2026 Official leaderboard
10 DeepSeek V4.1 Flash 22% Pi Sep 2026 Official leaderboard
11 GPT-6 Luna 21.5% Codex Sep 2026 Official leaderboard
12 Grok 4.6 21.3% Grok Build Aug 2026 Official leaderboard
13 Claude Sonnet 5 19.4% LSVP, Pi Jun 2026 Official leaderboard
14 Mistral Large 4 19.4% Pi Oct 2026 Official leaderboard
15 Gemini 4 Argon 19.1% Pi Sep 2026 Official leaderboard
16 Kimi K3 16.5% Pi Jul 2026 Official leaderboard
17 GLM-5.3 16.5% Pi Aug 2026 Official leaderboard
18 GPT-5.6 Sol 15.8% Codex Jul 2026 Official leaderboard
19 Gemini 3.8 Flash 15.8% Pi Sep 2026 Official leaderboard
20 GPT-5.6 Luna 15% Pi Jul 2026 Official leaderboard
21 Nemotron 3 Ultra 12.1% Pi Jun 2026 Official leaderboard
22 Nemotron 3.5 Lightning 30B-A3B 7.69% Pi Aug 2026 Official leaderboard

5 models have held number one on the official leaderboard since 2023

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

NVIDIA Anthropic
Own leaderboard 5 leaders

Source: Official NeuroscienceBench 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 Claude Opus 5.5 Claude Sonnet 5 Nemotron 3 Ultra 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 Claude Opus 5.5

Source: Official NeuroscienceBench 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 Science and reasoning

All 203 in Science and reasoning
  • GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics. Gemini 4 Carbon 97%
  • Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
  • BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
  • FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics. Intern-S2-397B 87%
  • HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels. Gemini 3 Pro 78.3%
  • LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%

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 (22 entries).
  • Pass Models scored 22 models we track.
  • Pass Newest score The newest is from November 2026, for Claude Fable 5.2.
  • Pass Frontier models 8 of the top 10 have a score, led by Claude Fable 5.2 (#2).
  • Pass Headroom The best is 41%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on benchmarks.bio: 36 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