Harness

opencode

opencode is strongest with qwen3.8-flash, 5th overall.

Best overall rank5th
Best partnerqwen3.8-flash
Strongest inPresentations
First places12 tasks
Pairings evaluated15 of 19 models
Time and cost, best pairingTime1098sCost$0.0322

Who opencode works best with

Valid evaluations covered 15 of 19 models. The other 4 have not been evaluated yet.

  1. qwen3.8-flash1088#5
  2. claude-opus-5-51082#6
  3. glm-5.3-prime1054#11
  4. gpt-6.1-sol1051#12
  5. claude-fable-5-11049#13
  6. gpt-6-astra1031#15
  7. qwen3.8-max1023#16
  8. gpt-5.6-terra1010#18
  9. gpt-5.6-sol1008#19
  10. gpt-6-sol976#23
  11. kimi-k3—Not evaluated
  12. deepseek-flash—Not evaluated
  13. kimi-k2.7-code—Not evaluated
  14. deepseek-v4-pro—Not evaluated

Places across 24 tasks

  1. 121st
  2. 42nd
  3. 33rd
  4. 34th
  5. 15th
  6. 16th and below

Most often 1st, in 12 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

Other harnesses