Expired75% confidenceFactTime unknown
In the Terminal-Bench evaluation, Codex scored 77.3 points and Claude Code scored 65.4 points.
1
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn the SWE-Bench evaluation, Claude Code scored 59 points and Codex scored 56.8 points.82% similarUnverified在SWE-Bench基准测试中，Codex得分在69-80分之间70% similarUnverifiedQwen3.6 27B scored 83 on Terminal-bench and approximately 59 on overall capability.65% similarVerifiedClaude Sonnet 5 scores 63.22% on SWE-bench Verified (Agentic Coding), approximately 6 percentage points behind Opus 4.8.65% similarUnverifiedIn the Terminal Bench 2.1 test, GPT-5.6 Ultra scored close to 92%, Fable 5 scored 88%, which are essentially on par considering the margin of error.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/5990API
curl https://kongchang.com/api/v1/knowledge/claims/5990MCP
get_claim(id=5990)