[
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "balatrobench",
  "type": "status_change",
  "old": "UNVERIFIED",
  "new": "ARCHIVE"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "balatrobench",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "balrog",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "claude-plays-pokemon-red",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "factorio-fle",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turn",
  "old": 7109,
  "new": 7167,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Location",
  "old": "Lavaridge Town Pokémon Center 1F",
  "new": "Lavaridge Town Gym B1F",
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "gpt-plays-pokemon",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "kaggle-chess",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "kradleverse-minecraft",
  "type": "value_change",
  "model": "claude-opus-4-6 (agent: Echo-Sinclair, OpenClaw)",
  "metric": "30-day win %",
  "old": "22%",
  "new": "23%",
  "source_url": "https://kradleverse.com/leaderboard"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "kradleverse-minecraft",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "pokemon-autonomous-completion",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:41:46-04:00",
  "run_id": "pokemon-vgc-bench",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:45:59-04:00",
  "run_id": "claude-plays-pokemon-red",
  "type": "value_change",
  "model": "Claude Opus 4.7",
  "metric": "Live now",
  "old": "no",
  "new": "yes",
  "source_url": "https://www.twitch.tv/claudeplayspokemon"
 },
 {
  "at": "2026-10-17T23:45:59-04:00",
  "run_id": "claude-plays-pokemon-red",
  "type": "status_change",
  "old": "PAUSED",
  "new": "LIVE"
 },
 {
  "at": "2026-10-17T23:45:59-04:00",
  "run_id": "gemini-flash-race-pokemon-blue",
  "type": "status_change",
  "old": "UNVERIFIED",
  "new": "PAUSED"
 },
 {
  "at": "2026-10-17T23:45:59-04:00",
  "run_id": "gemini-flash-race-pokemon-blue",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-17T23:45:59-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turn",
  "old": 7167,
  "new": 7175,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-17T23:47:09-04:00",
  "run_id": "gemini-flash-race-pokemon-blue",
  "type": "status_change",
  "old": "PAUSED",
  "new": "UNVERIFIED"
 },
 {
  "at": "2026-10-17T23:47:09-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turn",
  "old": 7175,
  "new": 7177,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-17T23:48:13-04:00",
  "run_id": "claude-plays-pokemon-red",
  "type": "value_change",
  "model": "Claude Opus 4.7",
  "metric": "Live now",
  "old": "yes",
  "new": "no",
  "source_url": "https://www.twitch.tv/claudeplayspokemon"
 },
 {
  "at": "2026-10-17T23:48:13-04:00",
  "run_id": "claude-plays-pokemon-red",
  "type": "status_change",
  "old": "LIVE",
  "new": "PAUSED"
 },
 {
  "at": "2026-10-17T23:48:13-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turn",
  "old": 7177,
  "new": 7178,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "gemini-flash-race-pokemon-blue",
  "type": "status_change",
  "old": "UNVERIFIED",
  "new": "RECENT"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "new_entry",
  "model": "Gemini 4 Argon",
  "metric": "Badges",
  "new": 8,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Badges",
  "old": 3,
  "new": 4,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "kaggle-go",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "kaggle-poker",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "kaggle-werewolf",
  "type": "status_change",
  "old": "RECENT",
  "new": "ARCHIVE"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "kaggle-werewolf",
  "type": "baseline",
  "note": "first automated fetch"
 },
 {
  "at": "2026-10-18T06:51:25-04:00",
  "run_id": "kradleverse-minecraft",
  "type": "value_change",
  "model": "claude-opus-4-6 (agent: Echo-Sinclair, OpenClaw)",
  "metric": "30-day win %",
  "old": "23%",
  "new": "24%",
  "source_url": "https://kradleverse.com/leaderboard"
 },
 {
  "at": "2026-10-18T07:04:13-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 4 Argon",
  "metric": "Turns",
  "old": 3509,
  "new": 3518,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T07:04:13-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turns",
  "old": 7890,
  "new": 7898,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T07:05:27-04:00",
  "run_id": "videogamebench-lite",
  "type": "new_entry",
  "model": "claude-3-7-sonnet-20250219",
  "metric": "Overall score",
  "new": "1.6%",
  "source_url": "https://www.vgbench.com/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T07:05:27-04:00",
  "run_id": "videogamebench-lite",
  "type": "new_entry",
  "model": "gemini-2.5-pro-preview-03-25",
  "metric": "Overall score",
  "new": "1.6%",
  "source_url": "https://www.vgbench.com/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T07:05:27-04:00",
  "run_id": "videogamebench-lite",
  "type": "new_entry",
  "model": "llama-4-maverick-17B-128E-Instruct-FP8",
  "metric": "Overall score",
  "new": "0%",
  "source_url": "https://www.vgbench.com/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T07:05:27-04:00",
  "run_id": "videogamebench-lite",
  "type": "new_entry",
  "model": "gemini-2.0-flash",
  "metric": "Overall score",
  "new": "0%",
  "source_url": "https://www.vgbench.com/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T07:05:27-04:00",
  "run_id": "videogamebench",
  "type": "new_entry",
  "model": "claude-3-7-sonnet-20250219",
  "metric": "Overall score",
  "new": "0%",
  "source_url": "https://www.vgbench.com/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T07:05:27-04:00",
  "run_id": "videogamebench",
  "type": "new_entry",
  "model": "llama-4-maverick-17B-128E-Instruct-FP8",
  "metric": "Overall score",
  "new": "0%",
  "source_url": "https://www.vgbench.com/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T07:05:27-04:00",
  "run_id": "videogamebench",
  "type": "new_entry",
  "model": "gemini-2.0-flash",
  "metric": "Overall score",
  "new": "0%",
  "source_url": "https://www.vgbench.com/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T12:49:52-04:00",
  "run_id": "kradleverse-minecraft",
  "type": "value_change",
  "model": "claude-opus-4-6 (agent: Echo-Sinclair, OpenClaw)",
  "metric": "30-day win %",
  "old": "24%",
  "new": "25%",
  "source_url": "https://kradleverse.com/leaderboard"
 },
 {
  "at": "2026-10-18T13:49:37-04:00",
  "run_id": "gpp-gemini-2-5-pro-blue-champion",
  "type": "new_record",
  "record_id": "gpp-gemini-2-5-pro-blue-champion",
  "model": "Gemini 2.5 Pro",
  "new": "Gemini 2.5 Pro becomes Champion in Pokémon Blue (development run, ~813 hours)",
  "source_url": "https://blog.jcz.dev/the-making-of-gemini-plays-pokemon",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:37-04:00",
  "run_id": "gpp-gemini-2-5-pro-blue-autonomous",
  "type": "new_record",
  "record_id": "gpp-gemini-2-5-pro-blue-autonomous",
  "model": "Gemini 2.5 Pro",
  "new": "Gemini 2.5 Pro beats Pokémon Blue with no manual interventions (~406 hours, 36,801 actions)",
  "source_url": "https://blog.jcz.dev/the-making-of-gemini-plays-pokemon",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:37-04:00",
  "run_id": "jev-standardagents-red-hof",
  "type": "new_record",
  "record_id": "jev-standardagents-red-hof",
  "model": "Jev",
  "new": "Jev enters the Pokémon Red Hall of Fame with Claude Opus 5 rebuilding its options live",
  "source_url": "https://jev-plays-pokemon.standardagents.ai/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:37-04:00",
  "run_id": "jev-frigade-red-hof",
  "type": "new_record",
  "record_id": "jev-frigade-red-hof",
  "model": "Jev",
  "new": "Jev beats Pokémon Red in 37h 40m with a guided, open-source harness",
  "source_url": "https://jev-pokemon.vercel.app/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:37-04:00",
  "run_id": "jev-astra-minecraft-dragon",
  "type": "new_record",
  "record_id": "jev-astra-minecraft-dragon",
  "model": "GPT-6 Astra",
  "new": "GPT-6 Astra + Jev kill the Ender Dragon in 8m 43s on a fixed seed with a pre-surveyed route (Peaceful)",
  "source_url": "https://x.com/rronak_/status/2101544156757950697",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:38-04:00",
  "run_id": "mineai-opus-5-minecraft-dragon",
  "type": "new_record",
  "record_id": "mineai-opus-5-minecraft-dragon",
  "model": "Claude Opus 5",
  "new": "Claude Opus 5 kills the Ender Dragon in a fresh Minecraft world in one unbroken 3h 56m session",
  "source_url": "https://huggingface.co/datasets/aibengineering/beat-the-game-minecraft",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:38-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 4 Argon",
  "metric": "Turns",
  "old": 3518,
  "new": 3707,
  "source_url": "https://gpp-viewer.arisef.org/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:38-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Badges",
  "old": 4,
  "new": 5,
  "source_url": "https://gpp-viewer.arisef.org/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T13:49:38-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turns",
  "old": 7898,
  "new": 8710,
  "source_url": "https://gpp-viewer.arisef.org/",
  "reviewed": true
 },
 {
  "at": "2026-10-18T14:05:38-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 4 Argon",
  "metric": "Turns",
  "old": 3707,
  "new": 3722,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T14:05:38-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turns",
  "old": 8710,
  "new": 8825,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T16:31:30-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 4 Argon",
  "metric": "Turns",
  "old": 3722,
  "new": 3797,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T16:31:30-04:00",
  "run_id": "gemini-plays-pokemon-emerald",
  "type": "value_change",
  "model": "Gemini 3.8 Flash",
  "metric": "Turns",
  "old": 8825,
  "new": 9274,
  "source_url": "https://gpp-viewer.arisef.org/"
 },
 {
  "at": "2026-10-18T16:31:30-04:00",
  "run_id": "kradleverse-minecraft",
  "type": "value_change",
  "model": "claude-opus-4-6 (agent: Echo-Sinclair, OpenClaw)",
  "metric": "30-day win %",
  "old": "25%",
  "new": "28%",
  "source_url": "https://kradleverse.com/leaderboard"
 }
]