Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Information Analysis and Processing on MARS Level 1 (test)
Loading...
1.7
Average Ranking (AI GPT-5)
Ours
1.4256
3.2778
5.13
6.9822
Nov 3, 2025
Average Ranking (AI GPT-5)
Average Ranking (Experts sampling)
Updated 11d ago
Evaluation Results
Method
Method
Links
Average Ranking (AI GPT-5)
Average Ranking (Experts sampling)
Ours
Param.=1800B
2025.11
1.7
1.2
Qwen3-235B-A
Param.=22B
2025.11
3.4
2.9
Llama-3.2-11B
Param.=11B
2025.11
5.1
6.1
Llama-Vision
Param.=11B
2025.11
5.4
7.2
Qwen-VL
Param.=7B
2025.11
5.56
7.9
Llama-4-Scout
Param.=17B
2025.11
5.9
6.89
GPT-oss
Param.=20B
2025.11
6.4
7.22
Llama-3.2-90B
Param.=90B
2025.11
6.8
4.8
Qwen2.5-VL
Param.=72B
2025.11
7.89
8
LLaVA-1.5
Param.=7B
2025.11
8.4
7
Qwen2-VL
Param.=72B
2025.11
8.56
6
Feedback
Search any
task
Search any
task