SpatialBench-Long (original study)
Agents complete 24 tasks in long spatial transcriptomics workflows. The authors compare their answers with results from the original analyses.
LatchBio distinguishes the original 24 tasks from the current 21. Its current board lists 45 model and harness configurations.
- Made by
- LatchBio
- Released
- May 2026
- Kind
- Genomics and life sciences
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Code sandbox
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Biology and medicine
- Strongest model tested
- GPT-5.5 #21 on the capability index
- Last model added
- May 2026
- Scores refreshed
- November 21st, 2026
2 models share the top score of 11.1% among models released by May 2026 2 models share the top score of 11.1% among models released by May 2026
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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 May 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-5.5 11.1%
- 2
Gemini 3.5 Flash 11.1%
- 3 Claude Opus 4.6 9.72%
- 4 Claude Opus 4.7 8.33%
- 5 Grok 4.20 6.94%
- 6 Kimi K2P6 5.56%
- 7 GPT-5.4 5.56%
- 8 Claude Sonnet 4.6 4.17%
- 9
Gemini 3.1 Pro 4.17%
- 10 Grok 4.3 4.17%
- 11 Gemini 2.5 Pro (snapshot unspecified) 1.39%
Source: The SpatialBench-Long (original study) paper
- 1 GPT-5.5 11.1%
- 2
Gemini 3.5 Flash 11.1%
- 3 Claude Opus 4.6 9.72%
- 4 Claude Opus 4.7 8.33%
- 5 Grok 4.20 6.94%
- 6 GPT-5.4 5.56%
- 7 Claude Sonnet 4.6 4.17%
- 8
Gemini 3.1 Pro 4.17%
- 9 Grok 4.3 4.17%
Source: The SpatialBench-Long (original study) paper
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 11.1% 5.7 to 20.4 | OpenAI Codex | Apr 2026 | Official leaderboard |
| 2 | | 11.1% 5.7 to 20.4 | Pi | May 2026 | Official leaderboard |
| 3 | Claude Opus 4.6 | 9.72% 4.8 to 18.7 | Claude Code | Feb 2026 | Official leaderboard |
| 4 | Claude Opus 4.7 | 8.33% 3.9 to 17 | Claude Code | Apr 2026 | Official leaderboard |
| 5 | Grok 4.20 | 6.94% 3 to 15.3 | Pi | Feb 2026 | Official leaderboard |
| 6 | Kimi K2P6 | 5.56% 2.2 to 13.4 | Pi | Official leaderboard | |
| 7 | GPT-5.4 | 5.56% 2.2 to 13.4 | Pi | Mar 2026 | Official leaderboard |
| 8 | Claude Sonnet 4.6 | 4.17% 1.4 to 11.6 | Pi | Feb 2026 | Official leaderboard |
| 9 | | 4.17% 1.4 to 11.6 | Pi | Feb 2026 | Official leaderboard |
| 10 | Grok 4.3 | 4.17% 1.4 to 11.6 | Pi | Apr 2026 | Official leaderboard |
| 11 | Gemini 2.5 Pro (snapshot unspecified) | 1.39% 0.3 to 7.5 | Pi | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 11.1% 5.7 to 20.4 | OpenAI Codex | Apr 2026 | Official leaderboard |
| 2 | | 11.1% 5.7 to 20.4 | Pi | May 2026 | Official leaderboard |
| 3 | Claude Opus 4.6 | 9.72% 4.8 to 18.7 | Claude Code | Feb 2026 | Official leaderboard |
| 4 | Claude Opus 4.7 | 8.33% 3.9 to 17 | Claude Code | Apr 2026 | Official leaderboard |
| 5 | Grok 4.20 | 6.94% 3 to 15.3 | Pi | Feb 2026 | Official leaderboard |
| 6 | GPT-5.4 | 5.56% 2.2 to 13.4 | Pi | Mar 2026 | Official leaderboard |
| 7 | Claude Sonnet 4.6 | 4.17% 1.4 to 11.6 | Pi | Feb 2026 | Official leaderboard |
| 8 | | 4.17% 1.4 to 11.6 | Pi | Feb 2026 | Official leaderboard |
| 9 | Grok 4.3 | 4.17% 1.4 to 11.6 | Pi | Apr 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The SpatialBench-Long (original study) paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SpatialBench-Long (original study) 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.
Versions
More in Biology and chemistry
- 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-5.6 Sol 31.5%
- MedChemBench (OpenAI) In use Models work through 99 medicinal chemistry problems drawn from recent papers and patents. Each task mixes prose with structures, assay tables and plots, then asks for the program’s next decision. GPT-6 Astra 83.8%
- 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%
- 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-Rosalind-6 61.3%
- ProtocolQA Open-Ended In use Models correct errors in published lab protocols using open-ended questions adapted from LAB-Bench ProtocolQA. Scored as pass@1. GPT-6 Cyber 47.2%
- MolecularIQ In use Models answer questions about molecular graphs, such as counting, indexing and constrained generation, and a symbolic checker verifies each answer. gpt-oss-120b 47.5%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (11 entries).
- Pass Models scored 9 models we track, plus 2 other entries on its leaderboard.
- Note Newest score The newest came 6 months ago, in May 2026, for Gemini 3.5 Flash. That’s expected for a test replaced by SpatialBench-Long.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.5 (#21).
- Pass Headroom The best is 11.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 13 rows for models we track and 2 other entries at the last read.
- Pass Last read November 21st, 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.