Skip to content

Releases: coder/balatrobench

v1.4.0

24 Jan 00:29

Choose a tag to compare

1.4.0 (2026-01-24)

Features

  • site: add twitch stream embed (4b09e47)

Bug Fixes

  • upload: add BUNNY_BASE_URL env var (46ab419)

Code Refactoring

  • cli: add required input-dir argument (958b442)

v1.3.0

21 Jan 20:22

Choose a tag to compare

1.3.0 (2026-01-21)

Features

  • site: add mistralai, qwen, z-ai, minimax, moonshotai colors (9d3dad5)
  • site: make the main plot twice as tall (e9370c1)
  • site: set min and max rotation for x axis (0d75476)

Bug Fixes

  • site: update CDN url (e0c6672)
  • upload: update the benchmarks path (13b3ee2)

v1.2.0

11 Jan 23:36

Choose a tag to compare

1.2.0 (2026-01-11)

Features

  • site: auto-detect environment from hostname (337c160)
  • site: update favicon to use balatrobench logo (6849d96)

Continuous Integration

  • release: add changelog-sections to release-please config (ce5b295)

v1.1.0

11 Jan 10:42

Choose a tag to compare

1.1.0 (2026-01-11)

Features

  • add serve target to Makefile (14b34d5)

Bug Fixes

v1.0.0

10 Jan 15:53

Choose a tag to compare

1.0.0 (2026-01-10)

Features

  • add about page (faf2c91)
  • add balatrobench logo (ea38c57)
  • add bar chart for avg rounds (ce9d2d5)
  • add benchmark for v0.7.0 (34a815e)
  • add benchmark for v0.8.1 (09f6d6d)
  • add benchmarks data for v0.6.0 (4a3d833)
  • add button to contribute your strategy (a94825c)
  • add community page (bac2147)
  • add config.js to control data source (dev and prod) (9f1305a)
  • add dark mode support for charts (b2130d3)
  • add data/community runs (58f505a)
  • add details table to leaderboard (e15e0fe)
  • add discord link and improve community page buttons (a444cc6)
  • add favicon (4d06723)
  • add files for version v2 (34e91b4)
  • add footer to all pages (1f898c5)
  • add gemini-2.5-pro to the leaderboard (d794f76)
  • add google color to bar chart (732ba52)
  • add hist and pie charts (86acd92)
  • add interactive run viewer with keyboard navigation (d72e555)
  • add labels to axes in the histogram (86c3fdb)
  • add mock data for community (61d287c)
  • add openai gpt-5 benchmark (6088226)
  • add pyproject.toml (4b5b8f4)
  • add robots.txt and sitemap.xml (1c6769d)
  • add run distribution chart (14dc13a)
  • add run viewer and version selector (f77ce8c)
  • add seed to detail page (2ccc51c)
  • add SEO optimization to the pages (aa6c0d9)
  • add template-based strategy system (f1218df)
  • add test and all targets to Makefile (adf7d4c)
  • add test coverage tooling (d0aaa31)
  • add time column to table and headers card (d83ac7b)
  • add total card to detail page (adf52e1)
  • add upload script (847a928)
  • add v0.11.0 benchmark data (0262094)
  • add v0.4.0 data structure and initial content (fbb8007)
  • analyzer: add benchmark analysis engine for BalatroLLM runs (abd56fa)
  • autogenerate version selector from manifest (67e2368)
  • balatrobench: add package exports and fix models types (8fec902)
  • centered model and vendor columns (84d3314)
  • cli: add CLI entry point for balatrobench command (1464c8b)
  • enhance frontend interface and functionality (bceb80a)
  • enhance responsiveness and data presentation (7207cd2)
  • enhance UI with detailed benchmark analytics (a923907)
  • enums: add enums for game configuration (5d4d7c0)
  • extractor: add JSONL parsing for requests and responses (3a2dc3d)
  • improve alignment for avg ± std dev (0bfc92a)
  • improve gamestate visualization (f3589b1)
  • improve headers legend (029823f)
  • improve HTML formatting and code structure (f502e1d)
  • improve nav bar (1cdce5c)
  • improve UI for nav bar and community btn (79f6f2c)
  • make the footer clickable (77ed17d)
  • models: add data models for benchmark files (f412a42)
  • move states into the header of the gamestate view (29d4c1f)
  • remove selector for version/strategy (480300a)
  • site: add svg assets (10b8525)
  • source: add TypedDicts for reading balatrollm source files (99c6ae1)
  • update application logic for v0.4.0 compatibility (9706b4b)
  • update benchmark data (e09cd19)
  • update benchmark data to v0.8.0 (8a6d362)
  • update benchmarks data to new format (8792aa0)
  • update colors for vendors (59eb553)
  • update community page to show strategies (01e25b5)
  • update data location and support external CDN for benchmarks (e594703)
  • update leaderboard layout (292dff9)
  • update script.js to support ?version= query param (c75b489)
  • update to v0.8.1 (440cc38)
  • update v0.7.0 benchmark results (4520a71)
  • use 0.8.1 data for community page (d822cba)
  • writer: add file I/O and WebP conversion for benchmark output (ccc3a97)

Bug Fixes

Read more