benchgap
General

DAYJOB leaderboard

As of 2026-11-18, the highest measured score on DAYJOB is 24.5% by Claude Opus 5.5. 94 more models have estimated scores, calibrated from the benchmarks they were measured on.

Measured scores: benchlm.ai.

#ModelScoreSource
1Claude Opus 5.524.5%measured
2Claude Sonnet 5.521.7%measured
3Gemini 4 Carbon19.7%measured
4Claude Fable 5.219.1%estimated ± 2.7 pp, medium confidence
5Claude Fable 5.118.9%estimated ± 2.7 pp, high confidence
6GPT-6 Astra17.4%measured
7GPT-6.2 Astra16.6%estimated ± 1.1 pp, medium confidence
8GPT-6.2 Sol16.6%estimated ± 1.1 pp, medium confidence
9GPT-6 Cyber16.6%estimated ± 1.1 pp, medium confidence
10Gemini 4 Argon15.7%measured
11GPT-6.1 Sol15.5%measured
12GPT-6.1 Terra13.6%estimated ± 1.1 pp, medium confidence
13Qwen3.8 Max13.6%estimated ± 3.2 pp, high confidence
14Claude Mythos 5.211.9%estimated ± 1.1 pp, medium confidence
15Claude Opus 511.7%measured
16GPT-5.5 Pro11.3%estimated ± 6.3 pp, medium confidence
17GPT-5.4 Pro9.4%estimated ± 6.3 pp, medium confidence
18Qwen3.8-27B7.3%estimated ± 3.2 pp, high confidence
19GPT-6 Sol6.8%measured
20Claude Mythos 55.3%estimated ± 1.1 pp, medium confidence
21Kimi K3.1 Pro4.7%estimated ± 1.1 pp, medium confidence
22DeepSeek V4.1 Flash 10174.4%estimated ± 2.6 pp, high confidence
23GPT-5.6 Sol4.2%measured
24Claude Mythos Preview3.8%estimated ± 1.1 pp, medium confidence
25MiniMax M3.1 Flash3.8%estimated ± 3.2 pp, high confidence
26Muse Spark Open3.0%estimated ± 3.2 pp, high confidence
27Hy4 preview2.9%estimated ± 3.2 pp, high confidence
28GPT-5.6 Terra2.8%measured
29Gemini 3.8 Flash2.6%measured
30Muse Wonder2.6%estimated ± 2.7 pp, high confidence
31DeepSeek V4 Pro2.3%estimated ± 3.2 pp, high confidence
32GLM-5.32.3%estimated ± 1.1 pp, medium confidence
33Ling 3.1 Flash2.1%estimated ± 3.2 pp, high confidence
34Claude Opus 4.82.0%measured
35MiMo-V2.6-Pro1.8%estimated ± 1.1 pp, medium confidence
36Claude Sonnet 51.7%measured
37Claude Haiku 5.51.4%estimated ± 2.7 pp, high confidence
38Hy31.4%estimated ± 5.5 pp, low confidence
39GPT-5.51.4%measured
40Grok 4.61.4%estimated ± 2.7 pp, high confidence
41GPT-5.21.4%estimated ± 2.7 pp, high confidence
42GPT-5.41.4%estimated ± 2.7 pp, high confidence
43Claude Fable 51.4%estimated ± 2.7 pp, high confidence
44Claude Opus 4.71.4%estimated ± 2.7 pp, high confidence
45Claude Opus 4.51.4%estimated ± 2.7 pp, high confidence
46Claude Opus 4.61.4%estimated ± 2.7 pp, high confidence
47Gemini 3.7 Flash1.4%estimated ± 2.7 pp, high confidence
48Gemini 3.6 Flash1.4%estimated ± 2.7 pp, medium confidence
49Grok 4.51.4%estimated ± 2.7 pp, medium confidence
50Kimi K2.61.4%estimated ± 2.7 pp, medium confidence
51Grok 4.71.4%estimated ± 2.7 pp, medium confidence
52Mistral Large 41.4%estimated ± 2.7 pp, medium confidence
53DeepSeek V4 Flash 07311.3%estimated ± 3.2 pp, high confidence
54Gemini 3.5 Flash1.3%estimated ± 3.2 pp, high confidence
55Qwen3.7 Max1.3%estimated ± 3.2 pp, high confidence
56o31.3%estimated ± 3.2 pp, high confidence
57GPT-51.3%estimated ± 3.2 pp, high confidence
58Qwen3.5 Flash1.3%estimated ± 3.2 pp, high confidence
59Qwen 3.6 Max (preview)1.3%estimated ± 3.2 pp, high confidence
60Qwen3.5 397B1.3%estimated ± 3.2 pp, high confidence
61Claude Sonnet 4.51.3%estimated ± 3.2 pp, high confidence
62Qwen3.5-122B-A10B1.3%estimated ± 3.2 pp, high confidence
63Qwen3.5 Plus1.3%estimated ± 3.2 pp, high confidence
64Qwen3.7 Plus1.3%estimated ± 3.2 pp, high confidence
65Claude Sonnet 4.61.3%estimated ± 3.2 pp, high confidence
66GPT-5.11.3%estimated ± 3.2 pp, high confidence
67GLM-5.21.3%estimated ± 3.2 pp, high confidence
68Qwen3.7 Flash1.3%estimated ± 3.2 pp, high confidence
69GPT-4o mini1.3%estimated ± 3.2 pp, high confidence
70Qwen3.6 Plus1.3%estimated ± 3.2 pp, high confidence
71GLM-5.3-Flash1.3%estimated ± 3.2 pp, high confidence
72GPT-4.1 mini1.3%estimated ± 3.2 pp, high confidence
73GPT-5.4 mini1.3%estimated ± 3.2 pp, high confidence
74o3-mini1.3%estimated ± 3.2 pp, high confidence
75GPT-5.4 nano1.3%estimated ± 3.2 pp, medium confidence
76o4-mini1.3%estimated ± 3.2 pp, medium confidence
77Qwen3 Max1.3%estimated ± 3.2 pp, medium confidence
78GPT-OSS 120B1.3%estimated ± 3.2 pp, medium confidence
79GPT-6 Luna1.2%measured
80SWE-2 Flash1.1%estimated ± 1.1 pp, medium confidence
81GPT-5.6 Luna1.1%measured
82Kimi K31.0%estimated ± 1.1 pp, low confidence
83Muse Spark 1.10.8%estimated ± 6.3 pp, medium confidence
84MiMo-V2.6-Flash0.7%estimated ± 1.1 pp, low confidence
85Grok 4.200.5%estimated ± 6.3 pp, medium confidence
86Seed 2.1 Turbo0.5%estimated ± 6.3 pp, medium confidence
87Muse Spark 1.30.4%estimated ± 3.2 pp, high confidence
88GLM-4.70.4%estimated ± 6.3 pp, medium confidence
89Inkling0.4%estimated ± 6.3 pp, medium confidence
90Seed 2.1 Pro0.4%estimated ± 6.3 pp, medium confidence
91GLM-5.10.4%estimated ± 6.3 pp, medium confidence
92Grok 4.30.4%estimated ± 6.3 pp, medium confidence
93Kimi K2.7 Code0.4%estimated ± 6.3 pp, low confidence
94GPT-4.10.4%estimated ± 6.3 pp, low confidence
95o10.4%estimated ± 6.3 pp, low confidence
96GPT-4o0.4%estimated ± 6.3 pp, low confidence
97Claude Haiku 4.50.4%estimated ± 6.3 pp, low confidence
98Claude 3 Opus0.4%estimated ± 6.3 pp, low confidence
99GPT-4.1 nano0.4%estimated ± 6.3 pp, low confidence
100Step 5 Preview0.1%estimated ± 3.2 pp, high confidence
101Gemini 3.1 Pro0.0%measured
102Gemini 3.5 Flash-Lite0.0%measured
103Gemini 3 Flash0.0%measured
104Gemma 4 26B A4B0.0%estimated ± 3.2 pp, medium confidence
105Gemma 4 31B0.0%estimated ± 3.2 pp, medium confidence
106Inkling-Small0.0%estimated ± 3.2 pp, medium confidence
107MAI-Thinking-10.0%estimated ± 3.2 pp, medium confidence
108MiniMax M30.0%estimated ± 3.2 pp, high confidence
109Muse Spark 1.20.0%estimated ± 6.3 pp, low confidence
110Nemotron 3 Ultra0.0%estimated ± 3.2 pp, medium confidence
111Qwen3.6-27B0.0%estimated ± 3.2 pp, medium confidence
112Qwen3.6-35B-A3B0.0%estimated ± 3.2 pp, medium confidence
113Beam 1.0 501B-A23B0.0%estimated ± 3.2 pp, medium confidence

All leaderboards

Agentic · terminal

Agentic · tools

Coding

Math

Knowledge & reasoning

Instruction following

Multilingual

Vision & documents

Long context

General