Unverified50% confidenceBenchmarkExact time
Compared to GPT-6 Astra, SWE-2's score trails by a few percentage points, but its cost is only one-quarter of the latter's.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/13/2026
First Seen
Valid until: 12/12/2026
Sources
Related Entities
Related Claims
UnverifiedSWE-2's benchmark score differs from that of competitor Fable 5.1 by less than one percentage point, but its cost is 64% lower.79% similarUnverifiedGPT-6 Astra at reasoning levels below max still could not reliably draw the pelican's legs on both sides of the frame; this issue was only resolved at the max level.70% similarUnverifiedGPT-5.6's Extreme High tier achieves a score of 53.6% for approximately $63, whereas Claude Sonnet in adaptive mode spends approximately $2,000 to achieve a score of only 40.5%.70% similarUnverifiedIn the initial publicly released SWE-bench results, GPT-4's resolution rate was only approximately 1.7%, Devin claimed to reach 13.86%, and SWE-agent reached 12.5%.69% similarUnverifiedIn SWE-bench testing, the early GPT-4 resolution rate was below 2%, while Claude 3.5 Sonnet broke through 49%.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/918911API
curl https://kongchang.com/api/v1/knowledge/claims/918911MCP
get_claim(id=918911)