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.
Claude Opus 4.8$5.00 to read · $25.00 to writePrice from Anthropic's own price page
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 - MCPQwen AgentWorld 397B A17B by 13.354.968.2+13.3
- AgentWorldBench - SWEQwen AgentWorld 397B A17B by 4.464.168.5+4.4
- AgentWorldBench - WebClaude Opus 4.8 by 3.754.751+3.7
- AgentWorldBench - SearchQwen AgentWorld 397B A17B by 2.735.137.8+2.7
- AgentWorldBench - OverallQwen AgentWorld 397B A17B by 2.156.658.7+2.1
- AgentWorldBench - TerminalClaude Opus 4.8 by 1.559.257.7+1.5
- AgentWorldBench - AndroidClaude Opus 4.8 by 1.361.560.2+1.3
- AgentWorldBench - OSQwen AgentWorld 397B A17B by 1.366.667.9+1.3
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.