Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

See the free Radar Brief

LABBench2: An Improved Benchmark for AI Systems Performing Biology Research (LABBench2)

A benchmark of realistic biology-research tasks involving literature, figures, tables, databases, and bioinformatics files.

Data verified 27 confirmed releases in the last 30 daysSee the free Radar Brief

Benchmark score on LABBench2 — September 2, 2026

We mirror the published score view for LABBench2. Gemini 3.8 Flash leads the public snapshot at 86.2%, followed by Claude Opus 5 (84.2%) and GPT-5.6 Sol (82.1%). We do not use these results to rank models overall.

6 modelsKnowledgeCurrentDisplay onlyUpdated September 2, 2026

Benchmark score table (6 models)

Score
1
Gemini 3.8 FlashGoogle · Closed
86.2%
2
Claude Opus 5Anthropic · Closed
84.2%
3
GPT-5.6 SolOpenAI · Closed
82.1%
4
Gemini 3.7 FlashGoogle · Closed
82.1%
5
GPT-5.6 TerraOpenAI · Closed
81.2%
6
Claude Sonnet 5Anthropic · Closed
80.1%

The published LABBench2 snapshot places Gemini 3.8 Flash first at 86.2%. The third row is 4.1 points behind. The broader top-10 range is 6.1 points, so many of the published results sit in a relatively narrow band.

6 models have been evaluated on LABBench2. The benchmark falls in the Knowledge category. This category carries a 12% weight in BenchLM.ai's overall scoring system. LABBench2 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About LABBench2

Year

2026

Tasks

Nearly 1,900 biology-research tasks

Format

Aggregate accuracy

Difficulty

Real-world biology research

LABBench2 expands LAB-Bench into nearly 1,900 more realistic scientific-research tasks. Google's Gemini 3.8 evaluation gives models a Linux terminal with bioinformatics tools, Python, R, and internet access, and reports the aggregate accuracy as display-only evidence.

BenchLM freshness & provenance

Version

LABBench2 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does LABBench2 measure?

A benchmark of realistic biology-research tasks involving literature, figures, tables, databases, and bioinformatics files.

Which model scores highest on LABBench2?

Gemini 3.8 Flash by Google currently leads with a score of 86.2% on LABBench2.

How many models are evaluated on LABBench2?

6 AI models have been evaluated on LABBench2 on BenchLM.

Last updated: September 2, 2026 · BenchLM version LABBench2 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.