Skip to content

Benchmark

xbench-DeepSearch

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

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

49.5%
Mean
53%
Median
3.5%
Std dev
46%
10th percentile
53%
90th percentile
46%
Min
46%53%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemini Pro· xbench53%
2Kimi K2.5Thinking· xbench46%