Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on ARC-IT
Loading...
95
Accuracy
Qwen3-30B-A3B
61.824
70.437
79.05
87.663
Mar 17, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-30B-A3B
Group=Larger, Configur...
2026.03
95
Qwen3-30B-A3B
Group=Larger, Configur...
2026.03
95
Gpt-oss-20b-high
Group=Larger, Configur...
2026.03
93.2
Gpt-oss-20b-high
Group=Larger, Configur...
2026.03
92.6
Qwen3-14B
Group=Larger, Configur...
2026.03
89.2
Qwen3-14B
Group=Larger, Configur...
2026.03
89.2
gemma-3-12b-it
Group=Larger, Configur...
2026.03
88.5
gemma-2-9b-it
Group=Comparable, Conf...
2026.03
88.4
gemma-3-12b-it
Group=Larger, Configur...
2026.03
88.1
gemma-2-9b-it
Group=Comparable, Conf...
2026.03
87.6
EngGPT2-16B-A3B
Group=Comparable, Conf...
2026.03
85.6
EngGPT2-16B-A3B
Group=Comparable, Conf...
2026.03
85.6
Llama-3.1-8B-Instruct
Group=Comparable, Conf...
2026.03
81.4
Llama-3.1-8B-Instruct
Group=Comparable, Conf...
2026.03
80
Moonlight-16B-A3B-Instruct
Group=Comparable, Conf...
2026.03
63.1
Moonlight-16B-A3B-Instruct
Group=Comparable, Conf...
2026.03
63.1
Feedback
Search any
task
Search any
task