Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Information Analysis and Processing on MARS Level 3 (Evaluation Set)
Loading...
1.9
Avg Rank (AI GPT-5)
Ours
1.608
3.579
5.55
7.521
Nov 3, 2025
Avg Rank (AI GPT-5)
Avg Rank (Experts Sampling)
Updated 11d ago
Evaluation Results
Method
Method
Links
Avg Rank (AI GPT-5)
Avg Rank (Experts Sampling)
Ours
Param.=1800B
2025.11
1.9
1.3
Qwen3-235B-A
Param.=22B
2025.11
2.3
4.4
Llama-4-Scout
Param.=17B
2025.11
4.5
6.4
Llama-Vision
Param.=11B
2025.11
5.5
6.2
Qwen-VL
Param.=7B
2025.11
6.2
7
Llama-3.2-11B
Param.=11B
2025.11
6.4
5.8
LLaVA-1.5
Param.=7B
2025.11
6.8
5.6
GPT-oss
Param.=20B
2025.11
7.3
6.6
Llama-3.2-90B
Param.=90B
2025.11
7.4
6.8
Qwen2-VL
Param.=72B
2025.11
8.5
7.7
Qwen2.5-VL
Param.=72B
2025.11
9.2
8.2
Feedback
Search any
task
Search any
task