BlogLLM Benchmark Scores as Published, Side by Side
LatchBio Capabilities: Results as Published
Every result the catalog holds for LatchBio Capabilities: 10 models from 3 developers, read from 4 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Science and MathMaintainer LatchBio (benchmarks.bio project)Data version 2026103001, as of 2026-10-30
LatchBio Capabilities is a composite score for how well AI agents analyse real biological data. Each component benchmark starts from a snapshot of real experimental data taken just before a key analysis step, and the agent must work out the biological result. A deterministic grader checks each answer, and the overall score is a weighted average of the pass rates.
LatchBio SingleCellBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 59.1% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: max; Tools: bash, file editor |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 61.2% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25; printed on 1 more page | - |
| Claude Mythos 5.1Anthropic, released 2026-09-01 | 61.9% | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25; printed on 1 more page | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 60.5% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25; printed on 1 more page | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 56.5% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 2 more pages | Effort: max; Tools: bash, file editor |
| Claude Mythos 5Anthropic, released 2026-06-09 | 59.3% | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25 | - |
LatchBio SpatialBench Verified
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 72.5% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: max; Tools: bash, file editor |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 72% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25; printed on 1 more page | - |
| Claude Mythos 5.1Anthropic, released 2026-09-01 | 77.6% | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25; printed on 1 more page | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 71.7% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25; printed on 1 more page | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 68.9% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 2 more pages | Effort: max; Tools: bash, file editor |
| Claude Mythos 5Anthropic, released 2026-06-09 | 69.2% | Anthropic, System Card: Claude Fable 5.1 & Claude Mythos 5.1checked 2026-10-25 | - |
LatchBio Capabilities v1.0 (overall score)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 47.4% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 43.1% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 40.2% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Grok 4.7xAI, released 2026-09-21 | 44.5% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: xhigh |
| Grok 4.6xAI, released 2026-08-12 | 43.3% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: high |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.