BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

BioMysteryBench leaderboard

As of 6 Nov 2026, the top score on BioMysteryBench is 81.1% by Claude Sonnet 5.5 (Anthropic), ahead of GPT-6.1 Sol at 79.6%, across 30 model configurations with a published result (Vals AI, result dated 5 Nov 2026). Each task hands the model a bioinformatics question and the data behind it, and expects the full analysis a research scientist would run. BioMysteryBench is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Claude Sonnet 5.5 holds the top BioMysteryBench score at 81.1% (Vals AI, 5 Nov 2026).
  • GPT-6.1 Sol is second on BioMysteryBench at 79.6% (Vals AI, 5 Nov 2026).
  • BioMysteryBench: End-to-end bioinformatics investigations from raw data to a conclusion. Run by Vals AI (Vals AI).
  • 30 model configurations have a published BioMysteryBench result on BenchLeader (BenchLeader, 6 Nov 2026).
  • BioMysteryBench does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

End-to-end bioinformatics investigations from raw data to a conclusion. Run by Vals AI.

Published by
Vals AI
Category
Knowledge
Index weight
Reference only
Models
30
Data as of
6 Nov 2026

Vals AI (vals.ai).

What the test looks like

Each task hands the model a bioinformatics question and the data behind it, and expects the full analysis a research scientist would run.

How it is scored

Percent of investigations reaching the correct conclusion, graded by Vals AI.

What to keep in mind

Small task set and long tasks, so scores move with single results.

Top 15
  1. 1Claude Sonnet 5.581.1%
  2. 2GPT-6.1 Sol (max)79.6%
  3. 3GPT-6 Astra (max)79.3%
  4. 4Claude Opus 579.3%
  5. 5Claude Opus 5.579.3%
  6. 6Gemini 4 Argon (high)76.3%
  7. 7Kimi K3.1 Pro (max)75.6%
  8. 8GPT-6 Sol (max)74.8%
  9. 9Muse Wonder Full (max)73.3%
  10. 10Kimi K3 (max)72.6%
  11. 11Grok 4.6 (high)72.2%
  12. 12GPT-5.6 Sol (max)71.1%
  13. 13Claude Haiku 5.570.4%
  14. 14Inkling 2 Small70.0%
  15. 15Grok 4.7 (xhigh)69.3%
30 of 30
#
1Claude Sonnet 5.581.1%–$3.742026-11-05
2GPT-6.1 Solmax79.6%67.3$0.3722026-11-05
3GPT-6 Astramax79.3%67.8$1.722026-11-05
4Claude Opus 579.3%65.2$3.292026-11-05
5Claude Opus 5.579.3%63.4$3.642026-11-05
6Gemini 4 Argonhigh76.3%66.0$5.712026-11-05
7Kimi K3.1 Promax75.6%–$0.7902026-11-05
8GPT-6 Solmax74.8%63.3$0.6622026-11-05
9Muse Wonder Fullmax73.3%62.9$3.472026-11-05
10Kimi K3max72.6%62.1$1.062026-11-05
11Grok 4.6high72.2%60.5$1.232026-11-05
12GPT-5.6 Solmax71.1%65.4$1.932026-11-05
13Claude Haiku 5.570.4%–$0.5132026-11-05
14NewInkling 2 Small70.0%57.4$0.2692026-11-05
15Grok 4.7xhigh69.3%58.3$2.492026-11-05
16Hy469.3%55.7$0.3622026-11-05
17MiMo-V2.6-Flash69.3%55.0$0.0502026-11-05
18DeepSeek V4.1 Flashhigh67.8%55.7$0.2332026-11-05
19Step 5 Preview67.4%54.9$0.4952026-11-05
20Muse Wondermax67.0%62.3$3.232026-11-05
21Mistral Large 4high67.0%49.5$1.052026-11-05
22Ember-167.0%–$0.9072026-11-05
23Muse Spark 1.2xhigh64.8%61.7$0.9952026-11-05
24DeepSeek V4 Flashhigh64.4%57.3$0.0392026-11-05
25Gemini 3.8 Flashhigh62.2%62.0$1.552026-11-05
26GPT-6 Lunamax61.5%56.7$0.0532026-11-05
27GPT-5.6 Lunamax61.5%56.3$0.0892026-11-05
28Gemini 3.1 Prohigh60.0%60.1$0.7132026-11-05
29Gemini 3.6 Flashhigh58.5%61.2$1.252026-11-05
30Beam 1.042.6%45.8–2026-11-05

More knowledge benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on BioMysteryBench

Cite as: BenchLeader, “BioMysteryBench leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/vals_biomysterybench.

BioMysteryBench: questions

What does BioMysteryBench measure?
Each task hands the model a bioinformatics question and the data behind it, and expects the full analysis a research scientist would run. Scores are reported in percent of tasks solved; higher is better.
What is the top score on BioMysteryBench?
As of 6 Nov 2026, the highest score on BioMysteryBench is 81.1% by Claude Sonnet 5.5 (result dated 5 Nov 2026), ahead of GPT-6.1 Sol at 79.6%. Scores come from Vals AI and are re-read daily.
Which AI model leads BioMysteryBench?
Claude Sonnet 5.5 leads BioMysteryBench with 81.1% as of 6 Nov 2026 (result dated 5 Nov 2026), ahead of GPT-6.1 Sol at 79.6%.
How many models have BioMysteryBench results?
30 model configurations have a BioMysteryBench result on BenchLeader, all taken from Vals AI.
Who runs BioMysteryBench and how often is it updated?
BioMysteryBench is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does BioMysteryBench count toward the BenchLeader Index?
No. BioMysteryBench is shown for reference but left out of the composite index.