Benchmark Almanac

Molecular Biology Capabilities Test

GPT-5.6 Sol 60% leads since Jun 2026 Only in system cards

Models answer expert-level molecular biology questions from SecureBio. Scored as accuracy.

200 text-only questions with a private holdout on everyday molecular biology methods. 14 PhD biologists scored about 34%. Modeled after VCT.

Made by SecureBio Genomics and life sciences Last in a system card Oct 2026 Last model added Oct 2026
Level
Expert Specialists with years of training, often over hours of work
Scored
Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers
Multiple choice
securebio.org
7
Models scored in lab cards
8
System cards report it, from 2 labs

GPT-5.6 Sol leads with 60%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 60.0 GPT-5.6 Sol
  2. 59.6 Muse Wonder Full
  3. 54.4 Muse Spark
  4. 53.2 Muse Spark 1.1
  5. 52.2 Muse Spark 1.3
  6. 48.0 GPT-5
  7. 32.7 Code World Model (CWM)
  1. 1 GPT-5.6 Sol 60%
  2. 2 Muse Wonder Full 59.6%
  3. 3 Muse Spark 54.4%
  4. 4 Muse Spark 1.1 53.2%
  5. 5 Muse Spark 1.3 52.2%
  6. 6 GPT-5 48%
  7. 7 Code World Model (CWM) 32.7%
#ModelScoreSettingDateSource
1 GPT-5.6 Sol 60% Jun 2026 Model card
2 Muse Wonder Full 59.6% Oct 2026 Model card
3 Muse Spark 54.4% Jun 2026 Model card
4 Muse Spark 1.1 53.2% Jul 2026 Model card
5 Muse Spark 1.3 52.2% Oct 2026 Model card
6 GPT-5 48% Aug 2025 Model card
7 Code World Model (CWM) 32.7% Oct 2025 Model card

3 models have held number one since 2023

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

OpenAI Meta
Lab claims 3 leaders
GPT-5.6 Sol 60%

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.6 Sol Muse Spark GPT-5 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.6 Sol GPT-5

Labs report it only in system cards

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.

8 system cards report it, from 2 labs

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
23 Oct 2026 Muse Spark 1.3 system card 52.2 MBCT accuracy, Muse Spark 1.3 (API) max, multiple-response MC (Table 1, Figure 1, 2.1.1.1) Bio and chem risk
12 Oct 2026 Muse Wonder Full model card 59.6 SecureBio MBCT, Muse Wonder Full (CBRN Capability Evaluations table, section 4). SecureBio average of MBCT, HPCT and VCT 60.7 Bio and chem risk
9 Jul 2026 GPT-5.6 Sol system card 60 SecureBio Molecular Biology Capabilities Test, strongest reported configuration (9.1.1.8) Bio and chem risk
9 Jul 2026 Muse Spark 1.1 system card 53.2 MBCT, Muse Spark 1.1 Helpful (Table 1, Figure 1) Bio and chem risk
25 Jun 2026 GPT-5.6 Sol system card 60 SecureBio Molecular Biology Capabilities Test, strongest reported configuration (9.1.1.8) Bio and chem risk
12 Jun 2026 Muse Spark system card 54.4 MBCT, Muse Spark Thinking (Table 1, Figure 1) Bio and chem risk
8 Oct 2025 Code World Model (CWM) technical report 32.7 Molecular Biology Capabilities Test (MBCT) (Table 9) Bio and chem risk
7 Aug 2025 GPT-5 system card 48 SecureBio Molecular Biology Capabilities Test, mean of n=10 (Table 15) Bio and chem risk

More in Biology and chemistry

All 96 in Biology and chemistry
  • SUPERChem In use Models solve 500 expert-written chemistry reasoning problems, offered in multimodal and text-only forms. Expert solution paths also allow a reasoning path score. Tencent Hy4 preview 66.4%
  • GeneBench Pro In use Agents analyze messy simulated genomics and biology datasets to estimate a decision-relevant quantity across 129 problems. Scored automatically against known answers. GPT-6 Astra 37.1%
  • LifeSciBench In use Models complete 750 expert-written life science research tasks, often with attached figures, tables, or sequence files. Graded against expert rubrics as score and pass rate. GPT-6 Astra 60.3%
  • MolecularIQ In use Models answer questions about molecular graphs, such as counting, indexing and constrained generation, and a symbolic checker verifies each answer. Intern-S2-397B 62.4%
  • TOMG-Bench In use Models generate molecules from natural language requests in three tasks: molecule editing, molecule optimization and customized generation. Each output is checked for validity and for meeting the requested properties. Intern-S2-397B 66.8%
  • BABE Fading Models reason from experimental results in peer-reviewed biology papers to draw conclusions, with causal and cross-scale inference. Seed2.0 Lite (0428) 57.9%