Unverified50% confidenceOpinionExact time
A score of about 65% on Terminal-Bench is already above average, but comparisons across different versions (such as 4.0) require caution, because the task set and scoring rules may be adjusted.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedOn the Terminal-Bench 2.0 benchmark, the same model Opus 4.6 scores from 60.45% to 82.02% under different harnesses (a gap of about 22 percentage points).70% similarUnverifiedThe Claude model's score on the Terminal Bench 4.0 terminal coding benchmark improved from 42% to nearly 56%.67% similarUnverifiedThe Terminal Bench score rose from 57 to 65.66% similarUnverifiedFable 5.1 scored 52.6% on the Terminal Bench Science 0.1 benchmark, more than doubling the score of its previous generation.66% similarUnverifiedTerminal-Bench 4.0 has a standard error of ±2.6 points, and Opus 5's 51.8% reproduced as 52.3%, which Anthropic calls noise.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1116633API
curl https://kongchang.com/api/v1/knowledge/claims/1116633MCP
get_claim(id=1116633)