Leaderboard

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

Consulting

Sales & operations management

Pairings
45
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
400600800100012001400

On the line

  1. opencode × qwen3.8-flashQuality873Cost$0.0316
  2. opencode × qwen3.7-plusQuality937Cost$0.0546
  3. codex × deepseek-flashQuality1070Cost$0.1690
  4. opencode × gpt-6.1-solQuality1267Cost$0.1909
  5. opencode × gpt-6-astraQuality1299Cost$1.0411
  6. opencode × claude-opus-5-5Quality1320Cost$2.6939
  7. claude_code × claude-fable-5-1Quality1387Cost$9.1779

All pairings

  1. 1claude_code×claude-fable-5-1Quality 1387Time 1428.9sCost $9.1779
  2. 2opencode×claude-opus-5-5Quality 1320Time 1402.4sCost $2.6939
  3. 3opencode×gpt-6-astraQuality 1299Time 549.7sCost $1.0411
  4. 4claude_code×claude-opus-5-5Quality 1278Time 843.4sCost $1.0674
  5. 5opencode×claude-fable-5-1Quality 1277Time 848.7sCost $2.1318
  6. 6opencode×gpt-6.1-solQuality 1267Time 426.6sCost $0.1909
  7. 7codex×gpt-6-astraQuality 1242Time 390sCost $0.5864
  8. 8opencode×gpt-5.6-solQuality 1166Time 812.6sCost $0.3843
  9. 9opencode×gpt-5.6-terraQuality 1152Time 512.2sCost $0.1957
  10. 10codex×gpt-6.1-solQuality 1148Time 427.5sCost $0.1939
  11. 11opencode×gpt-6-solQuality 1134Time 498.3sCost $0.2442
  12. 12codex×gpt-5.6-solQuality 1113Time 826.2sCost $0.4289
  13. 13codex×gpt-6-solQuality 1108Time 449.8sCost $0.2324
  14. 14codex×gpt-5.6-terraQuality 1099Time 457.4sCost $0.1948
  15. 15claude_code×deepseek-flashQuality 1091Time 1376.9sCost $0.2912
  16. 16opencode×deepseek-flashQuality 1083Time 1218.5sCost $0.2020
  17. 17kimi_cli×kimi-k3Quality 1082Time 1028.3sCost $1.1272
  18. 18codex×deepseek-flashQuality 1070Time 1169sCost $0.1690
  19. 19opencode×glm-5.3-primeQuality 1030Time 956.6sCost $0.6469
  20. 20codex×qwen3.8-maxQuality 1029Time 2629.2sCost $1.0574