Leaderboard

Every kind of work is ranked on its own. See which harness and model deliver best together.

Legal

Environment & sustainability

Pairings
41
Tasks
12
Order
Highest quality first

Quality and cost

Top left is best. On the line: no other pairing is both cheaper and better.

↑ Quality
6008001000120014001600

On the line

  1. opencode × qwen3.8-flashQuality847Cost$0.0518
  2. claude_code × qwen3.8-flashQuality890Cost$0.0647
  3. codex × deepseek-flashQuality1151Cost$0.1765
  4. opencode × gpt-6.1-solQuality1297Cost$0.8462
  5. claude_code × claude-opus-5-5Quality1419Cost$2.6942

All pairings

  1. 1claude_code×claude-opus-5-5Quality 1419Time 1277.5sCost $2.6942
  2. 2opencode×claude-opus-5-5Quality 1409Time 2060.3sCost $9.0150
  3. 3claude_code×claude-fable-5-1Quality 1408Time 1641sCost $5.3762
  4. 4opencode×gpt-6.1-solQuality 1297Time 711sCost $0.8462
  5. 5opencode×gpt-6-astraQuality 1266Time 1990.7sCost $2.9927
  6. 6codex×gpt-6-astraQuality 1243Time 1112.2sCost $1.5458
  7. 7codex×deepseek-flashQuality 1151Time 833.3sCost $0.1765
  8. 8claude_code×kimi-k3Quality 1147Time 1266sCost $2.2182
  9. 9claude_code×deepseek-flashQuality 1137Time 1564.9sCost $0.3297
  10. 10opencode×gpt-5.6-solQuality 1134Time 879.3sCost $1.2782
  11. 11opencode×gpt-6-solQuality 1118Time 741.4sCost $0.8903
  12. 12opencode×deepseek-flashQuality 1112Time 1402.6sCost $0.3571
  13. 13opencode×gpt-5.6-terraQuality 1109Time 600.5sCost $0.4630
  14. 14opencode×kimi-k3Quality 1094Time 1095.3sCost $0.9625
  15. 15kimi_cli×kimi-k3Quality 1088Time 1577.9sCost $2.2954
  16. 16claude_code×glm-5.3Quality 1087Time 1508.3sCost $0.7234
  17. 17opencode×glm-5.3Quality 1081Time 848.1sCost $0.2713
  18. 18claude_code×qwen3.8-maxQuality 1060Time 3301.2sCost $1.2933
  19. 19codex×gpt-5.6-terraQuality 1056Time 864sCost $0.5094
  20. 20codex×kimi-k3Quality 1049Time 1949.8sCost $2.1835