Share your thoughts, 1 month free Claude Pro on usSee more

Sequence Understanding on Sequence Understanding Benchmark Average of 10 tasks

100Answer Rate

DeepSeek-V3

Updated 1mo ago

Evaluation Results

Method	Links
DeepSeek-V3 2026.04		100	45.7
DeepSeek-V3 2026.04		100	44.5
DeepSeek-V3 2026.04		100	45.2
DeepSeek-V3 2026.04		100	50.9
Claude-3.7-Sonnet 2026.04		100	54.2
DeepSeek-R1 2026.04		99.9	61.1
DeepSeek-R1 2026.04		99.9	56.6
DeepSeek-R1 2026.04		99.9	70.5
Claude-3.7-Sonnet 2026.04		99.9	57.6
Claude-3.7-Sonnet 2026.04		99.9	79.1
DeepSeek-R1 2026.04		99.8	57.9
Claude-3.7-Sonnet 2026.04		99.8	57.3
GPT-4.1 2026.04		99.8	60
GPT-4.1 2026.04		99.6	61
GPT-4.1 2026.04		99.6	60
GPT-4.1 2026.04		99.5	82.7
GPT-4o 2026.04		99	46.4
GPT-4o 2026.04		98.6	44.5
GPT-4o 2026.04		98.6	59.1
GPT-4o 2026.04		98.5	51.5
Average 2026.04		92.8	68.9
Average 2026.04		90.5	51.6
Average 2026.04		90.3	48.9
Qwen3-30B-A3B 2026.04		90.2	80.7
Average 2026.04		89.9	48.7
Qwen3-8B 2026.04		87.3	69.6
Gemini-2.5-Pro 2026.04		84.6	79.1
Gemini-2.5-Pro 2026.04		83.4	58.9
Gemini-2.5-Pro 2026.04		82	56.9
Gemini-2.5-Pro 2026.04		81.8	48
Qwen3-30B-A3B 2026.04		81	52.3
Qwen3-30B-A3B 2026.04		80.9	52.7
Qwen3-30B-A3B 2026.04		80.6	54.3
Qwen3-8B 2026.04		79.5	40.3
Qwen3-8B 2026.04		79.4	45.5
QwQ-32B 2026.04		75.6	57.8
Qwen3-8B 2026.04		75.2	38.5
QwQ-32B 2026.04		72.7	34.2
QwQ-32B 2026.04		72.7	28.5
QwQ-32B 2026.04		72.2	28.9