BREAKING
DeepSeek V4 matches Sonnet 4.6
0
%
before
0
%
after
0
criteria
Same score, one-seventh the cost
DeepSeek V4 Pro
Open-weight
●
5% all-pass
●
~1/7 cost
Claude Sonnet 4.6
Closed
●
~5% all-pass
●
Baseline cost
Evolve the harness, not the model
1
Propose mechanism
↓
2
Verify effect
↓
3
Adopt or reject
File handling was the blind spot
Harness, Loop, Memory, Evals
AI NEWS BLITZ
An open model reached frontier scores on a legal benchmark with no weight changes.