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.
GPT-5.4$2.50 to read · $15.00 to writePrice from Artificial Analysis
Qwen AgentWorld 35B A3BNo 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 - MCPGPT-5.4 by 5.370.164.8+5.3
- AgentWorldBench - OSGPT-5.4 by 2.768.665.9+2.7
- AgentWorldBench - WebGPT-5.4 by 2.251.849.5+2.2
- AgentWorldBench - OverallGPT-5.4 by 1.958.356.4+1.9
- AgentWorldBench - AndroidGPT-5.4 by 1.86058.2+1.8
- AgentWorldBench - SWEtie66.365.6tie
- AgentWorldBench - Searchtie37.336.7tie
- AgentWorldBench - Terminaltie53.754tie
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.