Skip to content

Benchmark

MobileWorld

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
3
Scores recorded
4
Sources
2
IQ weight
No weight published

Score distribution

74.7%
Mean
77.8%
Median
3.3%
Std dev
70%
10th percentile
77.8%
90th percentile
70%
Min
70%77.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.8%
2Qwen3.8 MaxQwen3.8-Max release vision/video table · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.8%
3Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.1%
4Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.