Commit History

28 days ago

  1. Add GPT 6.1 Sol

    676755c
  2. Add Claude Opus 5.5, Claude Sonnet 5.5, GPT 6 Sol, Astra and Luna; update prices

    1ec3cbe
  3. Open source the eval harness

    7fd8268

  1. Add cost/point over time

    3fcd299

  1. Unify build script and add more models

    406eae5

  1. Add Qwen 3.8 27B (XHigh, Q4_K_XL)

    c0ff6a9

  1. Add Qwen 3.8 27B (Medium, Q4_K_XL)

    890124c

  1. Update generatedAt

    2f833d2
  2. Add Gemini 3.7 Flash (Medium)

    e0eb74c
  3. Fix incorrect release year

    d75a060
  4. Add Deepseek V4 Pro 0813 (High)

    2e10e8d

  1. Add Qwen 3.8 2.4T-A95B

    a4782f1

  1. Add Grok 4.6 (Medium)

    496bac5
  2. Add Nemotron 3.5 Lightning

    af4e4f8

  1. Add topic breakdown and details for Muse Glimmer 30B (Q4_K_XL)

    3d4ff5c
  2. Add Muse Glimmer 30B (Q4_K_XL)

    9c04c4a
  3. Update topic methodology to match new UI

    44d4222
  4. Major refactor and results explorer

    25cfbfb

  1. Add Deepseek V4 Flash 0731

    988702a

  1. Rerun GPT 5.6 Luna/Terra at new pricing

    89a790d

  1. Add topic breakdown for Qwen2.5-Coder-32B

    51f08f9
  2. Add Qwen 2.5 Coder 32B, Qwen 3 4B Instruct 2507, Deepseek R1 0528, and Devstral Small 2507

    bbd8973

  1. Add Qwen 3 Coder 30B-A3B, Claude Sonnet 4, Gemini 2.5 Pro, Gemini 3.1 Pro, GPT 5

    3bca641

  1. Display a lot more information

    778b7a2
  2. Breakdown QA scores by topic

    afbc698
  3. Add fail/noCode to leetcode results and the exact release date of the model

    d138419
  4. Start cost animation at constant offset

    372ac63
  5. Improve chart zoom/pan responsiveness

    3f0ee19
  6. Add chart zoom and adjust the copy

    a079f1c
  7. Rerun benchmarks with more robust retries for fewer no_answer failures

    dfbe9cd
  8. Improve chart readability

    a085767
  9. Add provider logos to make charts easier to read

    a666225

  1. Adjust price according to OpenRouter effective pricing

    c534a41
  2. Add avg noAnswer to overall table view

    8e00fc1
  3. Better breakdowns and table layout

    47ff52c
  4. Add Kimi K3

    43d0a9b
  5. More precise data entry with less rounding

    d291a2e
  6. Add Claude Opus 5

    ca980fd

  1. Add total eval costs

    c5a42ff
  2. Add Grok 4.5 (Medium)

    cb4281e

  1. Add GPT 5.6

    58de8fb

  1. Add Qwen 3.5 9B

    4217ba2

  1. Mention the number of knowledge questions

    a6655b5
  2. Use the same rounding as everyone else

    b7dce9d
  3. Improve tie behavior

    30419b5
  4. Add Claude Fable 5

    cf883f4
  5. Add llama 3.1 8b

    98a3e2e

  1. Initial commit

    b7dfece