Model
deepseek-v4-pro
deepseek-v4-pro is strongest with deepseek_harness, 34th overall.
Best overall rank34th
Best partner
deepseek_harness
deepseek_harnessStrongest inData analysis
First places2 tasks
Pairings evaluated1 of 5 harnesses
Time and cost, best pairingTime393.4sCost$0.1119
Who deepseek-v4-pro works best with
Valid evaluations covered 1 of 5 harnesses. The other 4 have not been evaluated yet.
- deepseek_harness949#34
claude_code—Not evaluated- kkimi_cli—Not evaluated
codex—Not evaluated
opencode—Not evaluated
Places across 24 tasks
- 21st
- 02nd
- 03rd
- 04th
- 05th
- 226th and below
Most often 6th and below, in 22 tasks.
Rank in each kind of work
Each row is a kind of work and each dot is one pairing's place in it; further left is better. Hover a dot for its name and place, or pick a name below to follow one pairing.
Where it places in each task
The number in each cell is a place: where that pairing ranked in that task, 1 being best, so 3 means 3rd. Hover a number to see how many pairings were ranked there. A dash means the pairing was not run on that task.
1st2nd3rd4th5th6th and below