Leaderboard

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

Consulting

Procurement management

Pairings
49
Tasks
6
Order
Highest quality first

Quality and cost

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

↑ Quality
4006008001000120014001600

On the line

  1. opencode × qwen3.8-flashQuality885Cost$0.0162
  2. opencode × glm-5.3Quality1000Cost$0.0501
  3. codex × deepseek-flashQuality1132Cost$0.1074
  4. codex × gpt-6-solQuality1133Cost$0.1761
  5. opencode × gpt-6-solQuality1247Cost$0.2022
  6. opencode × gpt-6.1-solQuality1366Cost$0.2064
  7. codex × gpt-6-astraQuality1394Cost$0.5984
  8. claude_code × claude-fable-5-1Quality1439Cost$2.0623

All pairings

  1. 1claude_code×claude-fable-5-1Quality 1439Time 694sCost $2.0623
  2. 2codex×gpt-6-astraQuality 1394Time 557.3sCost $0.5984
  3. 3opencode×claude-fable-5-1Quality 1370Time 609.8sCost $1.5754
  4. 4opencode×gpt-6.1-solQuality 1366Time 524.2sCost $0.2064
  5. 5opencode×gpt-6-astraQuality 1322Time 705sCost $0.7877
  6. 6claude_code×claude-opus-5-5Quality 1316Time 639.1sCost $1.3127
  7. 7opencode×claude-opus-5-5Quality 1291Time 849.7sCost $1.3661
  8. 8opencode×gpt-6-solQuality 1247Time 515.3sCost $0.2022
  9. 9codex×gpt-6.1-solQuality 1203Time 675.2sCost $0.2704
  10. 10codex×gpt-5.6-solQuality 1183Time 489.5sCost $0.2790
  11. 11opencode×kimi-k3Quality 1181Time 775.8sCost $0.3957
  12. 12codex×gpt-5.6-terraQuality 1169Time 501.6sCost $0.2515
  13. 13claude_code×kimi-k3Quality 1155Time 532.1sCost $0.6988
  14. 14codex×gpt-6-solQuality 1133Time 853.5sCost $0.1761
  15. 15codex×deepseek-flashQuality 1132Time 563sCost $0.1074
  16. 16codex×kimi-k3Quality 1122Time 954.8sCost $0.5302
  17. 17opencode×gpt-5.6-solQuality 1119Time 774.5sCost $0.5081
  18. 18kimi_cli×kimi-k3Quality 1111Time 907.5sCost $0.7706
  19. 19opencode×gpt-5.6-terraQuality 1098Time 520.1sCost $0.1786
  20. 20claude_code×deepseek-flashQuality 1079Time 1458.5sCost $0.1508