Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Information Analysis and Processing on MARS Level 2 (Evaluation Set)
Loading...
2.2
Average Ranking (AI GPT-5)
Ours
1.932
3.741
5.55
7.359
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
2.2
1.5
Qwen3-235B-A
Param.=22B
2025.11
2.6
4
Llama-Vision
Param.=11B
2025.11
4.8
5.5
Llama-3.2-11B
Param.=11B
2025.11
5.8
6.7
Llama-3.2-90B
Param.=90B
2025.11
6.1
6.1
GPT-oss
Param.=20B
2025.11
6.7
5.3
Qwen-VL
Param.=7B
2025.11
6.78
7.9
Llama-4-Scout
Param.=17B
2025.11
6.9
5.9
Qwen2-VL
Param.=72B
2025.11
7.3
7.9
Qwen2.5-VL
Param.=72B
2025.11
8.2
8.8
LLaVA-1.5
Param.=7B
2025.11
8.9
6.4
Feedback
Search any
task
Search any
task