Skip to content
Health Evals
Boards
Models
Compare
Coverage
Method
Data
Menu
Boards
Models
Compare
Coverage
Method
Data
Coverage
148 of 483 model and board pairs have a published result.
Cells are ranks within one board; read down a column.
Top of its board
Bottom of its board
No published result
Model by board grid. Cells give the rank within that board.
Model
HealthBench Professional
HealthBench
Health Optimization Bench
HealthBench Hard
WHBench
Artificial Analysis Healthcare & Medical Index
Health Optimization Bench: subject suites
GPT-5.6 Sol
10
/ 31
15
/ 28
6
/ 18
6
/ 19
9
/ 29
4
/ 16
Claude Fable 5
3
/ 31
5
/ 28
2
/ 18
4
/ 29
1
/ 16
Claude Fable 5.1
7
/ 31
8
/ 28
1
/ 18
2
/ 29
8
/ 16
Claude Opus 5
11
/ 31
1
/ 28
5
/ 18
3
/ 29
2
/ 16
GPT-6 Astra
1
/ 31
11
/ 28
3
/ 18
3
/ 19
4
/ 29
Claude Sonnet 5
13
/ 31
10
/ 28
13
/ 18
11
/ 16
GPT-5.4
24
/ 31
23
/ 28
14
/ 19
3
/ 22
GPT-5.6 Luna
18
/ 31
19
/ 28
8
/ 19
21
/ 29
GPT-5.6 Terra
14
/ 31
15
/ 28
7
/ 19
19
/ 29
GPT-6 Luna
8
/ 31
21
/ 28
10
/ 19
20
/ 29
GPT-6 Sol
8
/ 31
25
/ 28
12
/ 19
13
/ 29
Grok 4.6
23
/ 31
4
/ 18
12
/ 29
3
/ 16
Muse Spark
19
/ 31
9
/ 18
1
/ 19
7
/ 16
Claude Opus 5.5
4
/ 31
6
/ 28
1
/ 29
GPT OSS 120B
14
/ 28
13
/ 19
28
/ 29
GPT-5
25
/ 31
13
/ 28
4
/ 19
GPT-5.1
29
/ 31
27
/ 28
17
/ 19
GPT-5.2
26
/ 31
4
/ 28
2
/ 19
GPT-5.5
22
/ 31
18
/ 28
9
/ 19
GPT-5.5 Instant
30
/ 31
26
/ 28
18
/ 19
Inkling
12
/ 18
24
/ 29
10
/ 16
Kimi K3
7
/ 18
9
/ 29
6
/ 16
MAI-Thinking-1
31
/ 31
15
/ 18
14
/ 16
MiniMax M3
14
/ 18
23
/ 29
13
/ 16
Mistral Medium 3.5
17
/ 18
28
/ 29
15
/ 16
Claude Opus 4.8
15
/ 31
9
/ 28
Claude Sonnet 4.6
27
/ 31
2
/ 22
Claude Sonnet 5.5
2
/ 31
2
/ 28
Gemini 3.6
11
/ 18
9
/ 16
Gemini 3.8 Flash
10
/ 18
14
/ 29
GLM 5.2
16
/ 18
12
/ 16
GPT OSS 20B
28
/ 28
19
/ 19
GPT-5.3 Chat
22
/ 28
16
/ 19
Grok 4.7
16
/ 31
7
/ 29
Nemotron 3.5 Lightning
18
/ 18
16
/ 16
Baichuan-M3
3
/ 28
Claude Opus 4
14
/ 22
Claude Opus 4.6
1
/ 22
Claude Opus 4.7
21
/ 31
Claude Sonnet 4
15
/ 22
DeepSeek R1
10
/ 22
DeepSeek V4.1 Flash
16
/ 29
DeepSeek-V3.2
6
/ 22
Gemini 2.5 Flash
13
/ 22
Gemini 2.5 Pro
21
/ 22
Gemini 3 Flash
4
/ 22
Gemini 3.5 Flash Lite
25
/ 29
GLM 5.3
7
/ 29
GLM 5.3 Flash
9
/ 29
GPT-4.1
11
/ 22
GPT-4o
16
/ 22
Grok 3
7
/ 22
Grok 3 Mini
12
/ 22
Grok 4
9
/ 22
Llama 3.1 405B
20
/ 22
Llama 3.3 70B
19
/ 22
Llama 4 Maverick
17
/ 22
Llama 4 Scout
22
/ 22
Llama-3.1-Nemotron-70B-Instruct
18
/ 22
MiMo V2.6 Pro
14
/ 29
Mistral Large
8
/ 22
Muse Glimmer
27
/ 29
Muse Spark 1.1
12
/ 31
Muse Spark 1.3
6
/ 29
NVIDIA Nemotron 3 Ultra 550B A55B
25
/ 29
o3
5
/ 22
Qwen 3.8 27B
22
/ 29
Qwen3.8 Max
16
/ 29
Step 5
16
/ 29