Atlas

Benchmarks

TissueMicroscopyBench V1 (49 evaluations)

Benchmarks

Tests whether agents can analyze real tissue microscopy images: locating cells and structures, quantifying staining and morphology, and tracking changes over time and after treatment. Each of the 49 evaluations pairs real image data with a specific analysis question and a verifiable answer, and refusals, errors and unfinished runs count as failures. benchmarks.bio excludes it from its overall Capabilities score.

Models
14
Top score
25.9
Leader
GPT-6.1 Terra
Updated
Nov 11, 2026
Resolution
~1 mo
Sharp
Saturation
~May 2027
Projected
Signal
97thpercentile
192 benchmarks from 0.8 to 3.5218 benchmarks from 3.5 to 6.1128 benchmarks from 6.1 to 8.895 benchmarks from 8.8 to 11.567 benchmarks from 11.5 to 14.128 benchmarks from 14.1 to 16.814 benchmarks from 16.8 to 19.49 benchmarks from 19.4 to 22.111 benchmarks from 22.1 to 24.72 benchmarks from 24.7 to 27.46 benchmarks from 27.4 to 30.13 benchmarks from 30.1 to 32.73 benchmarks from 32.7 to 35.45 benchmarks from 35.4 to 38.01 benchmark from 38.0 to 40.71 benchmark from 40.7 to 43.41 benchmark from 43.4 to 46.01 benchmark from 62.0 to 64.6

24th strongest of 785

Signal-to-noise +24.68

Difficulty
88thpercentile
1 benchmark from 6.0 to 14.81 benchmark from 14.8 to 23.72 benchmarks from 32.5 to 41.41 benchmark from 41.4 to 50.22 benchmarks from 50.2 to 59.08 benchmarks from 59.0 to 67.97 benchmarks from 67.9 to 76.719 benchmarks from 76.7 to 85.623 benchmarks from 85.6 to 94.441 benchmarks from 94.4 to 103.331 benchmarks from 103.3 to 112.141 benchmarks from 112.1 to 120.947 benchmarks from 120.9 to 129.872 benchmarks from 129.8 to 138.660 benchmarks from 138.6 to 147.5119 benchmarks from 147.5 to 156.3126 benchmarks from 156.3 to 165.2115 benchmarks from 165.2 to 174.037 benchmarks from 174.0 to 182.818 benchmarks from 182.8 to 191.79 benchmarks from 191.7 to 200.51 benchmark from 200.5 to 209.44 benchmarks from 209.4 to 218.2

99th hardest of 785

Capability needed ≳ 170.7

Organizations
14 dated models · 5 frontier modelsClosed weightsOpen weights
Data: benchmarks.bioatlas.village.dev
#ModelSettingScoreSource
1GPT-6.1 Terranot reported · pi
25.9
benchmarks.bio V1 published results
2GPT-6.1 Solnot reported · pi
22.4
benchmarks.bio V1 published results
3Gemini 4 Argonnot reported · pi
21.8
benchmarks.bio V1 published results
4GPT-6 Astranot reported · pi
19.7
benchmarks.bio V1 published results
5Grok 4.6not reported · Grok Build
4.1
benchmarks.bio V1 published results
6Gemini 3.8 Flashnot reported · pi
3.4
benchmarks.bio V1 published results
7DeepSeek V4.1 Flashnot reported · pi
2.7
benchmarks.bio V1 published results
8GPT-5.6 Solnot reported · pi
2.0
benchmarks.bio V1 published results
9Mistral Large 4not reported · pi
2.0
benchmarks.bio V1 published results
10GLM-5.3not reported · pi
1.4
benchmarks.bio V1 published results
11GPT-6 Lunanot reported · pi
1.4
benchmarks.bio V1 published results
12GPT-5.6 Lunanot reported · pi
0.7
benchmarks.bio V1 published results
13Kimi K3not reported · pi
0.7
benchmarks.bio V1 published results
14Nemotron 3.5 Lightning 30B A3B (precision unspecified)not reported · pi
0.0
benchmarks.bio V1 published results
Loading Atlas data…