Atlas

Benchmarks

RareDiseaseBench V1 (35 evaluations)

Benchmarks

Tests whether agents can combine clinical, multiomic and functional data to diagnose and manage rare disease. Agents start from a clinical presentation and must request what they need from an isolated filesystem, and rubric grading scores how often they reach the right diagnosis and management plan. Refusals, errors and unfinished runs count as failures. 35 evaluations, which benchmarks.bio excludes from its overall Capabilities score.

Models
14
Top score
43.8
Leader
Gemini 4 Argon
Updated
Nov 6, 2026
Resolution
~1 mo
Sharp
Saturation
~Feb 2027
Projected
Signal
100thpercentile
205 benchmarks from 0.8 to 3.6219 benchmarks from 3.6 to 6.4134 benchmarks from 6.4 to 9.393 benchmarks from 9.3 to 12.155 benchmarks from 12.1 to 14.925 benchmarks from 14.9 to 17.713 benchmarks from 17.7 to 20.55 benchmarks from 20.5 to 23.37 benchmarks from 23.3 to 26.27 benchmarks from 26.2 to 29.01 benchmark from 29.0 to 31.83 benchmarks from 31.8 to 34.66 benchmarks from 34.6 to 37.43 benchmarks from 37.4 to 40.21 benchmark from 40.2 to 43.11 benchmark from 45.9 to 48.71 benchmark from 65.6 to 68.4

3rd strongest of 779

Signal-to-noise +40.67

Difficulty
80thpercentile
1 benchmark from 5.9 to 14.81 benchmark from 23.6 to 32.52 benchmarks from 32.5 to 41.31 benchmark from 41.3 to 50.22 benchmarks from 50.2 to 59.08 benchmarks from 59.0 to 67.97 benchmarks from 67.9 to 76.819 benchmarks from 76.8 to 85.623 benchmarks from 85.6 to 94.541 benchmarks from 94.5 to 103.331 benchmarks from 103.3 to 112.239 benchmarks from 112.2 to 121.148 benchmarks from 121.1 to 129.973 benchmarks from 129.9 to 138.859 benchmarks from 138.8 to 147.6118 benchmarks from 147.6 to 156.5127 benchmarks from 156.5 to 165.3113 benchmarks from 165.3 to 174.235 benchmarks from 174.2 to 183.117 benchmarks from 183.1 to 191.99 benchmarks from 191.9 to 200.81 benchmark from 200.8 to 209.64 benchmarks from 209.6 to 218.5

157th hardest of 779

Capability needed ≳ 166.8

14 dated models · 3 frontier modelsClosed weightsOpen weights
Data: benchmarks.bioatlas.village.dev
#ModelSettingScoreSource
1Gemini 4 Argonnot reported · pi
43.8
benchmarks.bio V1 published results
2GPT-6 Astranot reported · pi
33.3
benchmarks.bio V1 published results
3GPT-6.1 Solnot reported · pi
27.6
benchmarks.bio V1 published results
4GPT-6.1 Terranot reported · pi
25.7
benchmarks.bio V1 published results
5GPT-5.6 Solnot reported · pi
13.3
benchmarks.bio V1 published results
6Grok 4.6not reported · pi
4.8
benchmarks.bio V1 published results
7Gemini 3.8 Flashnot reported · pi
2.9
benchmarks.bio V1 published results
8Mistral Large 4not reported · pi
1.9
benchmarks.bio V1 published results
9GPT-5.6 Lunanot reported · pi
0.9
benchmarks.bio V1 published results
10DeepSeek V4.1 Flashnot reported · pi
0.0
benchmarks.bio V1 published results
11GLM-5.3not reported · pi
0.0
benchmarks.bio V1 published results
12GPT-6 Lunanot reported · pi
0.0
benchmarks.bio V1 published results
13Kimi K3not reported · pi
0.0
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…