Scores updated · 8 tests both models report · How we compare
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
DeepSeek-V4-Pro$0.43 to read · $0.87 to writePrice from Artificial Analysis
Qwen AgentWorld 397B A17BNo current price is tracked.
Every test, side by side
All 8 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results8 tests
- AgentWorldBench - SearchQwen AgentWorld 397B A17B by 10.227.637.8+10.2
- AgentWorldBench - SWEQwen AgentWorld 397B A17B by 9.159.468.5+9.1
- AgentWorldBench - TerminalQwen AgentWorld 397B A17B by 6.451.357.7+6.4
- AgentWorldBench - OverallQwen AgentWorld 397B A17B by 5.75358.7+5.7
- AgentWorldBench - AndroidQwen AgentWorld 397B A17B by 555.260.2+5
- AgentWorldBench - MCPQwen AgentWorld 397B A17B by 4.963.368.2+4.9
- AgentWorldBench - OSQwen AgentWorld 397B A17B by 4.263.767.9+4.2
- AgentWorldBench - Webtie50.351tie
Questions people ask
How do you compare the two?
We use the 8 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.