DataCurve
An organization that operates AI model evaluation leaderboards, conducting cross-model comparative benchmarking using a unified agent framework to provide independent benchmark data.
Timeline (last 90 days)
Google's methodology PDF states that Argon's Deep SWE result was self-calculated, GPT-6 Astra's figure comes from the DataCurve public leaderboard, and Claude's figure comes from Anthropic's system card.
On the unified agent setup leaderboard actually operated by DataCurve, three models are tied for first place at 74%, including Google's Gemini 3.8 Flash, while Argon is not listed.
All Facts (2)
Google's methodology PDF states that Argon's Deep SWE result was self-calculated, GPT-6 Astra's figure comes from the DataCurve public leaderboard, and Claude's figure comes from Anthropic's system card.
50%UnverifiedOn the unified agent setup leaderboard actually operated by DataCurve, three models are tied for first place at 74%, including Google's Gemini 3.8 Flash, while Argon is not listed.
50%