benchgap
General

DAYJOB Healthcare leaderboard

As of 2026-11-18, the highest measured score on DAYJOB Healthcare is 25.2% by Claude Opus 5.5. 93 more models have estimated scores, calibrated from the benchmarks they were measured on.

Measured scores: benchlm.ai.

#ModelScoreSource
1Claude Opus 5.525.2%measured
2Claude Fable 5.218.2%estimated ± 4.0 pp, medium confidence
3Claude Sonnet 5.516.0%measured
4Gemini 4 Carbon15.6%measured
5Gemini 4 Argon11.6%measured
6GPT-6.2 Astra11.2%estimated ± 1.1 pp, low confidence
7GPT-6.2 Sol11.2%estimated ± 1.1 pp, low confidence
8GPT-6 Cyber11.2%estimated ± 1.1 pp, low confidence
9GPT-6 Astra11.2%measured
10Claude Fable 5.111.1%estimated ± 4.0 pp, high confidence
11GPT-6.1 Terra11.1%estimated ± 1.1 pp, medium confidence
12GPT-6.1 Sol10.8%measured
13Claude Opus 59.2%measured
14GPT-5.5 Pro8.3%estimated ± 6.1 pp, low confidence
15GPT-5.4 Pro6.8%estimated ± 6.1 pp, low confidence
16Muse Wonder5.5%estimated ± 4.0 pp, high confidence
17Qwen3.8-27B5.2%estimated ± 4.7 pp, high confidence
18Claude Haiku 5.53.1%estimated ± 4.0 pp, high confidence
19GPT-6 Sol2.8%measured
20Claude Mythos 5.22.7%estimated ± 1.5 pp, medium confidence
21MiniMax M3.1 Flash2.3%estimated ± 4.7 pp, high confidence
22DeepSeek V4.1 Flash 10172.2%estimated ± 2.1 pp, high confidence
23GPT-5.6 Terra2.0%measured
24Muse Spark Open1.7%estimated ± 4.7 pp, high confidence
25Hy4 preview1.6%estimated ± 4.7 pp, high confidence
26Claude Mythos 51.5%estimated ± 1.5 pp, medium confidence
27Kimi K3.1 Pro1.5%estimated ± 1.5 pp, medium confidence
28Claude Mythos Preview1.5%estimated ± 1.5 pp, medium confidence
29GLM-5.31.5%estimated ± 1.5 pp, medium confidence
30MiMo-V2.6-Pro1.5%estimated ± 1.5 pp, medium confidence
31Kimi K31.5%estimated ± 1.5 pp, low confidence
32MiMo-V2.6-Flash1.5%estimated ± 1.5 pp, low confidence
33SWE-2 Flash1.5%estimated ± 1.5 pp, medium confidence
34Gemini 3.8 Flash1.2%measured
35GPT-5.6 Luna1.2%measured
36GPT-5.6 Sol1.2%measured
37GPT-6 Luna1.2%measured
38DeepSeek V4 Pro1.1%estimated ± 4.7 pp, high confidence
39Ling 3.1 Flash0.9%estimated ± 4.7 pp, high confidence
40Claude Opus 4.80.8%measured
41Claude Sonnet 4.50.7%estimated ± 4.2 pp, high confidence
42Claude Sonnet 4.60.7%estimated ± 4.2 pp, high confidence
43DeepSeek V4 Flash 07310.7%estimated ± 4.2 pp, high confidence
44Gemini 3.5 Flash0.7%estimated ± 4.2 pp, high confidence
45GLM-5.20.7%estimated ± 4.2 pp, high confidence
46GLM-5.3-Flash0.7%estimated ± 4.2 pp, high confidence
47GPT-4.1 mini0.7%estimated ± 4.2 pp, high confidence
48GPT-4o mini0.7%estimated ± 4.2 pp, high confidence
49GPT-50.7%estimated ± 4.2 pp, high confidence
50GPT-5.10.7%estimated ± 4.2 pp, high confidence
51GPT-5.4 mini0.7%estimated ± 4.2 pp, high confidence
52GPT-5.4 nano0.7%estimated ± 4.2 pp, medium confidence
53GPT-OSS 120B0.7%estimated ± 4.2 pp, medium confidence
54Inkling-Small0.7%estimated ± 4.2 pp, medium confidence
55MiniMax M30.7%estimated ± 4.2 pp, high confidence
56Muse Spark 1.30.7%estimated ± 4.2 pp, high confidence
57Nemotron 3 Ultra0.7%estimated ± 4.2 pp, high confidence
58o30.7%estimated ± 4.2 pp, high confidence
59o3-mini0.7%estimated ± 4.2 pp, high confidence
60o4-mini0.7%estimated ± 4.2 pp, medium confidence
61Qwen3.5-122B-A10B0.7%estimated ± 4.2 pp, high confidence
62Qwen3.5 397B0.7%estimated ± 4.2 pp, high confidence
63Qwen3.5 Flash0.7%estimated ± 4.2 pp, high confidence
64Qwen3.5 Plus0.7%estimated ± 4.2 pp, high confidence
65Qwen3.6-27B0.7%estimated ± 4.2 pp, high confidence
66Qwen3.6-35B-A3B0.7%estimated ± 4.2 pp, high confidence
67Qwen 3.6 Max (preview)0.7%estimated ± 4.2 pp, high confidence
68Qwen3.6 Plus0.7%estimated ± 4.2 pp, high confidence
69Qwen3.7 Flash0.7%estimated ± 4.2 pp, high confidence
70Qwen3.7 Max0.7%estimated ± 4.2 pp, high confidence
71Qwen3.7 Plus0.7%estimated ± 4.2 pp, high confidence
72Qwen3.8 Max0.7%estimated ± 4.2 pp, high confidence
73Qwen3 Max0.7%estimated ± 4.2 pp, medium confidence
74Grok 4.60.4%estimated ± 4.0 pp, high confidence
75Muse Spark 1.10.4%estimated ± 6.1 pp, low confidence
76Grok 4.200.2%estimated ± 6.1 pp, low confidence
77Muse Spark 1.20.2%estimated ± 6.1 pp, low confidence
78Seed 2.1 Turbo0.1%estimated ± 6.1 pp, low confidence
79GLM-4.70.1%estimated ± 6.1 pp, low confidence
80Inkling0.1%estimated ± 6.1 pp, low confidence
81Seed 2.1 Pro0.1%estimated ± 6.1 pp, low confidence
82GLM-5.10.1%estimated ± 6.1 pp, low confidence
83Grok 4.30.1%estimated ± 6.1 pp, low confidence
84Kimi K2.7 Code0.1%estimated ± 6.1 pp, low confidence
85GPT-4.10.1%estimated ± 6.1 pp, low confidence
86o10.1%estimated ± 6.1 pp, low confidence
87GPT-4o0.1%estimated ± 6.1 pp, low confidence
88Claude Haiku 4.50.1%estimated ± 6.1 pp, low confidence
89Claude 3 Opus0.1%estimated ± 6.1 pp, low confidence
90GPT-4.1 nano0.1%estimated ± 6.1 pp, low confidence
91Claude Fable 50.0%estimated ± 4.0 pp, high confidence
92Claude Opus 4.50.0%estimated ± 4.0 pp, high confidence
93Claude Opus 4.60.0%estimated ± 4.0 pp, high confidence
94Claude Opus 4.70.0%estimated ± 4.0 pp, high confidence
95Claude Sonnet 50.0%measured
96Gemini 3.1 Pro0.0%measured
97Gemini 3.5 Flash-Lite0.0%measured
98Gemini 3.6 Flash0.0%estimated ± 4.0 pp, medium confidence
99Gemini 3.7 Flash0.0%estimated ± 4.0 pp, high confidence
100Gemini 3 Flash0.0%measured
101Gemma 4 26B A4B0.0%estimated ± 4.7 pp, medium confidence
102Gemma 4 31B0.0%estimated ± 4.7 pp, medium confidence
103GPT-5.20.0%estimated ± 4.0 pp, high confidence
104GPT-5.40.0%estimated ± 4.0 pp, high confidence
105GPT-5.50.0%measured
106Grok 4.50.0%estimated ± 4.0 pp, medium confidence
107Grok 4.70.0%estimated ± 4.0 pp, medium confidence
108Kimi K2.60.0%estimated ± 4.0 pp, medium confidence
109MAI-Thinking-10.0%estimated ± 4.7 pp, medium confidence
110Mistral Large 40.0%estimated ± 4.0 pp, medium confidence
111Beam 1.0 501B-A23B0.0%estimated ± 4.7 pp, medium confidence
112Step 5 Preview0.0%estimated ± 4.7 pp, high confidence

All leaderboards

Agentic · terminal

Agentic · tools

Coding

Math

Knowledge & reasoning

Instruction following

Multilingual

Vision & documents

Long context

General