Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Root Cause Analysis on SFT data Easy (seen)
Loading...
77.4
Accuracy (%)
OpsLLM-32B
0.024
20.112
40.2
60.288
Apr 6, 2026
Accuracy (%)
Updated 28d ago
Evaluation Results
Method
Method
Links
Accuracy (%)
OpsLLM-32B
LLM Category=OpsLLM
2026.04
77.4
OpsLLM-14B
LLM Category=OpsLLM
2026.04
53.2
OpsLLM-7B
LLM Category=OpsLLM
2026.04
38.7
GPT-5.2
LLM Category=Closed-so...
2026.04
23.3
Qwen3-Next-80b-a3b-Thinking
LLM Category=Open-sour...
2026.04
21.8
Qwen-Plus-2025-09-11
LLM Category=Closed-so...
2026.04
21.5
Qwen3-Max-2025-09-23
LLM Category=Closed-so...
2026.04
20.8
Zhiyu-32B
LLM Category=Open-sour...
2026.04
14.1
R1-Distill-SRE-Qwen-32B-INT8
LLM Category=Open-sour...
2026.04
12.6
Moonshot-Kimi-K2-Instruct
LLM Category=Open-sour...
2026.04
11.6
Deepseek-v3.2-exp
LLM Category=Open-sour...
2026.04
10.4
Qwen2.5-32B-Instruct
LLM Category=Base LLM
2026.04
10.1
Qwen2.5-14B-Instruct
LLM Category=Base LLM
2026.04
9
Qwen2.5-7B-Instruct
LLM Category=Base LLM
2026.04
8
aiops-qwen-4b
LLM Category=Open-sour...
2026.04
7.9
Qwen-Turbo-2025-07-15
LLM Category=Closed-so...
2026.04
7.2
R1-Distill-SRE-Qwen-7B
LLM Category=Open-sour...
2026.04
3
Feedback
Search any
task
Search any
task