Partially Verified65% confidenceBenchmarkExact time
In the legal work test, Argon scored 19.6% and Fable scored 6.7%, giving Argon nearly a threefold advantage.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedArgon scored 77.9% on Deep SWE V1, 51.3% on Automation Bench, 91.7% on LV Bench, and 19.6% on the legal agent evaluation.75% similarUnverifiedIn the chart reading test, Argon scored 71.6% and Fable 46.2%, a gap of more than 25 percentage points, the largest single gap in the entire comparison.75% similarUnverifiedIn the machine learning and science category, Argon won 3 to 1, but lost the terminal science test (57.6 vs. 68.1), which is GPT-6's largest margin over Argon.72% similarUnverifiedOn the Harvey Legal Agent benchmark, Gemini 4 Argon reaches 19.6%, versus a maximum of 6.7% for competitors.71% similarUnverifiedIn the spreadsheet test, Argon scored 38%, Opus 30%, and Astra 23%.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036623API
curl https://kongchang.com/api/v1/knowledge/claims/1036623MCP
get_claim(id=1036623)