Published battle records

Battles

One published battle is one qualifying evaluation group. Pairwise comparisons are on the battle page. Repeated missing difficulty is not listed as a result.

Newest published battleQuality
4/5Composer 2.5
4/5Grok 4.6
3/5GPT-5.6 Luna
4/5GPT-5.6 Sol
2/5GPT-5.6 Terra
Composer 2.5, Grok 4.6, GPT-5.6 Sol share the highest scoreSep 19, 2026 20:22:04 UTC

155 battles. Newest published time first.

  1. View Quality battle, Sep 19, 2026 20:22:04 UTC
    4/5
    4/5
    3/5
    4/5
    2/5

    Quality

    Winners4 of 5

    1. Composer 2.54of 5
    2. Grok 4.6 via Cursor4of 5
    3. GPT-5.6 Sol4of 5
    4. GPT-5.6 Luna3of 5
    5. GPT-5.6 Terra2of 5
  2. View Quality battle, Sep 19, 2026 19:23:05 UTC
    4/5
    4/5
    4/5

    Quality

    Winners4 of 5

    1. DeepSeek Flash4of 5
    2. GPT-5.6 Sol4of 5
    3. Grok 4.64of 5
  3. View Quality battle, Sep 14, 2026 19:41:07 UTC
    4/ 5GPT-5.6 Sol
    VS
    4/ 5Qwen 3.7 Flashvia OpenRouter

    Quality

    Winners4 of 5

    1. GPT-5.6 Sol4of 5
    2. Qwen 3.7 Flash via OpenRouter4of 5
  4. View Quality battle, Sep 14, 2026 18:18:15 UTC
    4/5
    5/5
    5/5

    Quality

    Winners5 of 5

    1. GPT-5.6 Sol5of 5
    2. Grok 4.65of 5
    3. DeepSeek Flash4of 5
  5. View Quality battle, Sep 14, 2026 18:02:25 UTC
    5/5
    2/5
    5/5

    Quality

    Winners5 of 5

    1. DeepSeek Flash5of 5
    2. Grok 4.65of 5
    3. GPT-5.6 Sol2of 5
  6. View Quality battle, Sep 14, 2026 17:06:19 UTC
    4/5
    4/5
    4/5

    Quality

    Winners4 of 5

    1. Nemotron 3 Super 120B A12B4of 5
    2. GPT-5.6 Sol4of 5
    3. Grok 4.64of 5
  7. View Quality battle, Sep 14, 2026 15:48:59 UTC
    5/ 5Claude Sonnet 5via Cursor
    VS
    5/ 5GPT-5.6 Sol

    Quality

    Winners5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. GPT-5.6 Sol5of 5
  8. View Quality battle, Sep 13, 2026 23:27:30 UTC
    5/5
    5/5
    4/5

    Quality

    Winners5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. GPT-5.6 Sol5of 5
    3. Grok 4.64of 5
  9. View Quality battle, Sep 13, 2026 22:50:05 UTC
    4/ 5Claude Sonnet 5via Cursor
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winners4 of 5

    1. Claude Sonnet 5 via Cursor4of 5
    2. GPT-5.6 Sol4of 5
  10. View Quality battle, Sep 13, 2026 22:19:39 UTC
    5/ 5Claude Sonnet 5via Cursor
    VS
    5/ 5GPT-5.6 Sol

    Quality

    Winners5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. GPT-5.6 Sol5of 5
  11. View Quality battle, Sep 13, 2026 22:14:05 UTC
    5/ 5Claude Sonnet 5via Cursor
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. GPT-5.6 Sol4of 5
  12. View Quality battle, Sep 13, 2026 21:34:30 UTC
    5/ 5Claude Sonnet 5via Cursor
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. GPT-5.6 Sol4of 5
  13. View Quality battle, Sep 13, 2026 21:24:30 UTC
    5/5
    4/5
    5/5

    Quality

    Winners5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. GPT-5.6 Sol5of 5
    3. DeepSeek Flash4of 5
  14. View Quality battle, Sep 13, 2026 17:50:37 UTC
    4/5
    1/5
    5/5
    5/5

    Quality

    Winners5 of 5

    1. GPT-5.6 Sol5of 5
    2. Grok 4.65of 5
    3. DeepSeek Flash4of 5
    4. Nemotron 3.5 Lightning 30B A3B1of 5
  15. View Quality battle, Sep 13, 2026 17:24:49 UTC
    2/ 5GPT-5.6 Sol
    VS
    4/ 5Grok 4.6

    Quality

    Winner4 of 5

    1. Grok 4.64of 5
    2. GPT-5.6 Sol2of 5
  16. View Quality battle, Sep 13, 2026 14:46:39 UTC
    5/5
    4/5
    4/5

    Quality

    Winner5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. DeepSeek Flash4of 5
    3. GPT-5.6 Sol4of 5
  17. View Quality battle, Sep 13, 2026 14:24:12 UTC
    4/5
    5/5
    5/5

    Quality

    Winners5 of 5

    1. DeepSeek Flash5of 5
    2. GPT-5.6 Sol5of 5
    3. Claude Sonnet 5 via Cursor4of 5
  18. View Quality battle, Sep 13, 2026 06:48:36 UTC
    5/5
    4/5
    4/5

    Quality

    Winner5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. Composer 2.54of 5
    3. DeepSeek Flash4of 5
  19. View Quality battle, Sep 13, 2026 00:38:02 UTC
    5/5
    4/5
    5/5
    4/5

    Quality

    Winners5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. DeepSeek Flash5of 5
    3. Composer 2.54of 5
    4. GPT-5.6 Sol4of 5
  20. View Quality battle, Sep 12, 2026 23:24:42 UTC
    5/ 5GPT-5.6 Sol
    VS
    5/ 5Grok 4.6

    Quality

    Winners5 of 5

    1. GPT-5.6 Sol5of 5
    2. Grok 4.65of 5
  21. View Quality battle, Sep 12, 2026 20:57:04 UTC
    5/5
    5/5
    5/5
    4/5
    4/5
    4/5
    +4

    Quality

    Winners5 of 5

    1. Claude Sonnet 5 via Cursor5of 5
    2. Composer 2.55of 5
    3. GLM 5.2 via Cursor5of 5
    4. GPT-5.6 Sol5of 5
    5. Grok 4.55of 5
    6. DeepSeek Flash4of 5
    7. Kimi K3 via NVIDIA4of 5
    8. Nemotron 3 Super 120B A12B4of 5
    9. Grok 4.64of 5
    10. Nemotron 3.5 Lightning 30B A3B3of 5
  22. View Quality battle, Sep 12, 2026 18:56:30 UTC
    4/ 5Nemotron 3.5 Lightning 30B A3B
    VS
    4/ 5Grok 4.6

    Quality

    Winners4 of 5

    1. Nemotron 3.5 Lightning 30B A3B4of 5
    2. Grok 4.64of 5
  23. View Quality battle, Sep 12, 2026 15:50:11 UTC
    4/ 5Composer 2.5
    VS
    3/ 5DeepSeek Flash

    Quality

    Winner4 of 5

    1. Composer 2.54of 5
    2. DeepSeek Flash3of 5
  24. View Quality battle, Sep 12, 2026 07:55:13 UTC
    4/ 5DeepSeek Flash
    VS
    4/ 5Grok 4.6

    Quality

    Winners4 of 5

    1. DeepSeek Flash4of 5
    2. Grok 4.64of 5
  25. View Quality battle, Sep 12, 2026 00:06:31 UTC
    5/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol4of 5
  26. View Quality battle, Sep 11, 2026 23:36:59 UTC
    5/ 5Fable 5.1
    VS
    5/ 5GPT-5.6 Sol

    Quality

    Winners5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol5of 5
  27. View Quality battle, Sep 11, 2026 23:28:12 UTC
    5/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol4of 5
  28. View Quality battle, Sep 11, 2026 22:13:28 UTC
    4/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winners4 of 5

    1. Fable 5.14of 5
    2. GPT-5.6 Sol4of 5
  29. View Quality battle, Sep 11, 2026 21:33:23 UTC
    5/ 5Fable 5.1
    VS
    3/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol3of 5
  30. View Quality battle, Sep 11, 2026 21:16:27 UTC
    5/ 5Fable 5.1
    VS
    3/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol3of 5
  31. View Quality battle, Sep 11, 2026 20:39:54 UTC
    5/ 5Fable 5.1
    VS
    5/ 5GPT-5.6 Sol

    Quality

    Winners5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol5of 5
  32. View Quality battle, Sep 11, 2026 20:26:53 UTC
    5/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol4of 5
  33. View Quality battle, Sep 11, 2026 20:07:02 UTC
    5/5
    4/5
    4/5

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. DeepSeek Flash4of 5
    3. GPT-5.6 Sol4of 5
  34. View Quality battle, Sep 11, 2026 17:56:47 UTC
    4/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winners4 of 5

    1. Fable 5.14of 5
    2. GPT-5.6 Sol4of 5
  35. View Quality battle, Sep 11, 2026 17:20:04 UTC
    4/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winners4 of 5

    1. Fable 5.14of 5
    2. GPT-5.6 Sol4of 5
  36. View Quality battle, Sep 11, 2026 17:18:16 UTC
    5/ 5Fable 5.1
    VS
    5/ 5GPT-5.6 Sol

    Quality

    Winners5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol5of 5
  37. View Quality battle, Sep 11, 2026 17:02:58 UTC
    5/5
    4/5
    4/5

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol4of 5
    3. Grok 4.64of 5
  38. View Quality battle, Sep 11, 2026 16:57:01 UTC
    5/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol4of 5
  39. View Quality battle, Sep 11, 2026 16:44:46 UTC
    5/ 5Fable 5.1
    VS
    3/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol3of 5
  40. View Quality battle, Sep 11, 2026 16:26:46 UTC
    5/ 5Fable 5.1
    VS
    4/ 5GPT-5.6 Sol

    Quality

    Winner5 of 5

    1. Fable 5.15of 5
    2. GPT-5.6 Sol4of 5

PreviousNext

Difficulty is published only when every score in the battle recorded the same low, medium, high, or critical label. Otherwise it is not recorded. Prompts and code are not published.