Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Coding Agent Capacity on SpreadsheetBench Verified
Loading...
82.3
Score
Seed2.0 Lite
57.132
63.666
70.2
76.734
Jun 30, 2026
Score
Updated 24d ago
Evaluation Results
Method
Method
Links
Score
Seed2.0 Lite
2026.06
82.3
Seed2.0 Pro
2026.06
79.1
Claude-Opus-4.5
2026.06
78.6
Claude-Sonnet-4.5
2026.06
75.9
Gemini-3-pro High
2026.06
70.8
GPT-5.2 High
2026.06
69.9
Gemini-3-Flash High
2026.06
65.7
GPT-5-mini High
2026.06
58.1
Feedback
Search any
task
Search any
task