Leaderboard

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

Finance

Financial customer service

Pairings
49
Tasks
5
Order
Highest quality first

Quality and cost

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

↑ Quality
600800100012001400

On the line

  1. opencode × qwen3.8-flashQuality752Cost$0.0116
  2. opencode × qwen3.7-plusQuality808Cost$0.0217
  3. claude_code × qwen3.8-flashQuality809Cost$0.0350
  4. codex × qwen3.7-plusQuality812Cost$0.0395
  5. claude_code × qwen3.7-plusQuality868Cost$0.0396
  6. codex × deepseek-flashQuality999Cost$0.0415
  7. deepseek_harness × deepseek-flashQuality1045Cost$0.0468
  8. claude_code × deepseek-flashQuality1099Cost$0.0627
  9. codex × gpt-6-solQuality1176Cost$0.1257
  10. opencode × gpt-5.6-terraQuality1181Cost$0.1406
  11. codex × gpt-6.1-solQuality1288Cost$0.2006
  12. claude_code × claude-fable-5-1Quality1295Cost$0.9975
  13. claude_code × claude-opus-5-5Quality1349Cost$1.0133
  14. opencode × claude-fable-5-1Quality1363Cost$1.3375

All pairings

  1. 1opencode×claude-fable-5-1Quality 1363Time 483.1sCost $1.3375
  2. 2claude_code×claude-opus-5-5Quality 1349Time 447.2sCost $1.0133
  3. 3opencode×claude-opus-5-5Quality 1329Time 791.8sCost $1.0218
  4. 4claude_code×claude-fable-5-1Quality 1295Time 335.6sCost $0.9975
  5. 5codex×gpt-6.1-solQuality 1288Time 447.3sCost $0.2006
  6. 6opencode×gpt-6.1-solQuality 1263Time 447.4sCost $0.2068
  7. 7codex×gpt-6-astraQuality 1259Time 268.4sCost $0.3970
  8. 8opencode×gpt-5.6-solQuality 1251Time 411sCost $0.3884
  9. 9claude_code×kimi-k3Quality 1209Time 301.5sCost $0.2926
  10. 10opencode×kimi-k3Quality 1199Time 347.9sCost $0.2117
  11. 11codex×gpt-5.6-solQuality 1191Time 381sCost $0.2650
  12. 12opencode×gpt-5.6-terraQuality 1181Time 412.8sCost $0.1406
  13. 13codex×gpt-6-solQuality 1176Time 370.2sCost $0.1257
  14. 14codex×kimi-k3Quality 1163Time 459.9sCost $0.3324
  15. 15kimi_cli×kimi-k3Quality 1136Time 574.8sCost $0.3289
  16. 16claude_code×deepseek-flashQuality 1099Time 562.7sCost $0.0627
  17. 17opencode×gpt-6-solQuality 1098Time 342.5sCost $0.1458
  18. 18opencode×glm-5.3-primeQuality 1087Time 480.6sCost $0.2142
  19. 19claude_code×qwen3.8-maxQuality 1084Time 1245.5sCost $0.7143
  20. 20codex×gpt-5.6-terraQuality 1048Time 361.7sCost $0.1638