Unverified50% confidenceBenchmarkExact time
On Proximal's Frontier SWE benchmark (20 hours per task), Argon scored 55 and Astra 65.5.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedIn testing, GPT-6 Sol consumed approximately 50% of its quota after completing all five cases over five hours, while Astra consumed close to 90% to complete the same tasks.57% similarUnverifiedThe Talus model was trained from scratch on a single RTX 5060 (8 GB VRAM), accumulating approximately 4.5 hours of training across multiple versions.56% similarUnverifiedGemini 4 Argon Long Decode Continuation requires setting background=True and store=true, with max_output_tokens higher than 65,536, advancing in hops of at most 64K tokens, and running for up to 24 hours.53% similarUnverifiedZ.ai's peak hours are Monday to Friday 14:00 to 18:00 Singapore time (UTC+8), totaling 20 hours per week; outside peak hours, model usage is billed at 50% of the standard rate.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059527API
curl https://kongchang.com/api/v1/knowledge/claims/1059527MCP
get_claim(id=1059527)