Commit Graph

Select branches

Hide Pull Requests

add-spark-x2-pelican-cycling

main

Mono Color

• 69eaada1af chore: 项目已迁移至 Gitee/GitHub，仅保留迁移说明 (tombstone) main shuiyuPyLab 2026-08-09 10:16:33 +08:00
• f2d31a620b chore: 项目已迁移至 Gitee/GitHub，仅保留迁移说明 (tombstone) shuiyuPyLab 2026-08-09 09:58:34 +08:00
• 42a78d4a06 chore: relicense to MIT shuiyu 2026-08-02 18:46:00 +08:00
• adccd71f04 fix: move artifact to two-level artifactDir path add-spark-x2-pelican-cycling shuiyu67 2026-07-18 07:54:45 +08:00
• 79f6fcb41b fix: remove emojis from pelican-cycling SVG shuiyu67 2026-07-18 00:49:20 +08:00
• 07c124c8e0 feat: add Spark X2 pelican-cycling run shuiyu67 2026-07-18 00:42:34 +08:00
• 6580a7e931 Reorder cases: Turf War (04) before CS Dust2 (05) Jesse Zhang 2026-07-17 02:31:08 +01:00
• 65b4d476a1 chore: sync README registry [skip ci] github-actions[bot] 2026-07-17 00:46:52 +00:00
• bf0cb78d19 validate-data: handle agent-kind cases (turf-war) Jesse ZhangandClaude Opus 4.8 2026-07-17 01:46:31 +01:00
• 63570b1e6e Add Kimi K3 (Kimi Code, Max) — mythos, pelican, turf-war 蚕食 Jesse ZhangandClaude Opus 4.8 2026-07-17 01:22:54 +01:00
• 5e154e2309 Add Inkling (Thinking Machines Lab, Tinker Web xHigh) — mythos-craft + pelican Jesse ZhangandClaude Opus 4.8 2026-07-16 15:54:23 +01:00
• f2919d801b Add Kimi K3 (Kimi Web Max) mythos-craft run Jesse ZhangandClaude Opus 4.8 2026-07-16 15:39:38 +01:00
• 4b2a9e0173 Register Gemini 3.1 Pro (AntiGravity) turf-war run (寒冰王座) — mid-tier, even with baseline Jesse Zhang 2026-07-14 17:05:30 +01:00
• 1c4e949930 Register Fable 5 CC Max turf-war run (地头蛇) — solid strong performer Jesse Zhang 2026-07-14 17:01:56 +01:00
• 0d4baeeae4 Register Fable 5 CC xhigh turf-war run (画地为牢) — aggressive, opposite of the High turtle Jesse Zhang 2026-07-14 15:41:20 +01:00
• 1f084eb34f turf-war prompt: agents write to a file, not 'output' — reword the chatbox-flavored line Jesse Zhang 2026-07-14 14:50:24 +01:00
• 33e69b253e turf-war prompt: revert to incremental file-writing (per-response max_tokens is independent per edit; one giant write hits the cap incl. thinking tokens) Jesse Zhang 2026-07-14 14:31:09 +01:00
• 52996604bf turf-war prompt: write policy in one compact pass (no incremental rewrites, no giant tables) to avoid output-token-limit failures Jesse Zhang 2026-07-14 14:27:59 +01:00
• 90500bb8d6 Register Sonnet 5 CC Max (卷地风); add precise root-cause diagnosis to underperformer notes (Terra/Opus-xhigh/Fable-high) Jesse Zhang 2026-07-14 13:52:28 +01:00
• e215627e68 Register three Claude turf-war runs: Fable 5 CC High, Opus 4.8 CC Max/xhigh (self-named) Jesse Zhang 2026-07-14 12:40:01 +01:00
• 7d9dd07cc6 turf-war prompt: file-capable harnesses build the file incrementally (avoid single-output truncation on long policies); still no test runs Jesse Zhang 2026-07-14 12:04:12 +01:00
• d3b92ccee8 turf-war: Terra did self-name — register agentName 拓荒狐 Jesse Zhang 2026-07-14 03:46:13 +01:00
• 2a024a9dc8 Register three turf-war runs: GPT-5.6-Sol (Codex CLI max/xhigh), GPT-5.6-Terra (Codex CLI xhigh) Jesse Zhang 2026-07-14 03:34:46 +01:00
• ce9fd8bafe turf-war prompt: opponents are other Agents (model x harness), not 'AI models' Jesse Zhang 2026-07-14 03:19:40 +01:00
• 43a70bd651 turf-war prompt: maintainer-filled [This run] line (model x harness x effort, target filename) Jesse Zhang 2026-07-14 03:09:38 +01:00
• 9cd85bad21 turf-war prompt: deliver a file (save turf-war.js in file-capable harnesses, print content otherwise) Jesse Zhang 2026-07-14 03:07:30 +01:00
• 5c2a55bbb2 turf-war prompt: agents name themselves (fun name, <=5 chars zh / one short word en) Jesse Zhang 2026-07-14 03:00:28 +01:00
• 379ab28279 turf-war prompt: forbid web search / skills / external tools / test runs (world-knowledge only) Jesse Zhang 2026-07-14 02:55:04 +01:00
• 6dccc35cd8 Turf War is maintainer-run: no artifact PRs, policies stay private (anti-scouting); README case list updated to five cases Jesse Zhang 2026-07-14 02:50:27 +01:00
• 50fb9978dc Add case 05 Turf War (kind: agent) + agent-case contribution guide Jesse Zhang 2026-07-14 02:23:59 +01:00
• 1142b7dfde chore: sync README registry [skip ci] github-actions[bot] 2026-07-13 23:08:59 +00:00
• e3a60756f9 chore: regroup registry order by vendor Jesse ZhangandClaude Opus 4.8 2026-07-14 00:08:00 +01:00
• cbfce3b7cc feat: add cs-dust2 React case with two model takes + react kind support Jesse ZhangandClaude Opus 4.8 2026-07-13 18:58:50 +01:00
• c4cc293748 chore: sync README registry [skip ci] github-actions[bot] 2026-07-13 13:04:58 +00:00
• e166e31d92 feat(gem3.1proais):add Gemini 3.1 Pro AiStudio High skeleton-watch benchmark (#33) _‭⁧HachiMahiro哈基寻⁧‭ 2026-07-13 21:04:30 +08:00
• 7475999bff feat: Add DeepSeek V4 Flash with Claude Code Max run mythos-craft (#34) Chang ZhouandAv1dity 2026-07-13 21:04:27 +08:00
• a1802f0baf chore: sync README registry [skip ci] github-actions[bot] 2026-07-09 23:38:19 +00:00
• 5d52843621 fix: order GPT-5.5 Pro below GPT-5.6 (newest-first within OpenAI) Jesse ZhangandClaude Opus 4.8 2026-07-10 00:37:50 +01:00
• 64c033c5a7 chore: sync README registry [skip ci] github-actions[bot] 2026-07-09 22:09:38 +00:00
• b8ed871bc0 docs: document multi-take variant arrays in AGENTS.md Jesse ZhangandClaude Opus 4.8 2026-07-09 23:09:15 +01:00
• 64609bd6c8 feat: add GPT-5.6-Terra and alternate takes for GPT-5.6-Sol Jesse ZhangandClaude Opus 4.8 2026-07-09 23:09:15 +01:00
• 97e9a860a1 chore: sync README registry [skip ci] github-actions[bot] 2026-07-09 19:24:14 +00:00
• e14d6cd59f feat: add Grok 4.5 benchmark results (#31) mintcolorandDuJiabao 2026-07-10 03:23:47 +08:00
• 807bdac433 feat: add GPT-5.6-Sol benchmark results (#32) ZidongChen25 2026-07-09 20:23:36 +01:00
• 2192d05ac8 chore: sync README registry [skip ci] github-actions[bot] 2026-07-06 23:26:03 +00:00
• ffdd06626f feat: add skeleton-watch and pelican-cycling for Gemini 3.1 Pro × Gemini Web × Deep Think (#30) lupan-luand卢盼 2026-07-07 07:25:40 +08:00
• ada382b2dc chore: sync README registry [skip ci] github-actions[bot] 2026-07-03 21:43:24 +00:00
• 47a02cb481 feat: add Gemini 3.1 Pro × Gemini Web × Deep Think for mythos-craft (#29) lupan-luand卢盼 2026-07-04 05:43:04 +08:00
• 6c87c23963 chore: sync README registry [skip ci] github-actions[bot] 2026-07-02 16:15:51 +00:00
• 1a6b884f75 contrib: MiMo V2.5 (High) all cases BaiLin-William 2026-07-03 00:15:27 +08:00
• acb27270f0 docs: scope Codex review for benchmark artifacts Jesse Zhang 2026-07-02 17:08:18 +01:00
• c726210500 chore: sync README registry [skip ci] github-actions[bot] 2026-07-02 01:00:01 +00:00
• 5823fed8e1 Add Claude Fable 5 Claude Code xhigh skeleton-watch run Jesse Zhang 2026-07-02 01:59:34 +01:00
• 4d466f74cb docs: add default-harness (no extra skills) self-check to PR template Jesse ZhangandClaude Opus 4.8 2026-06-24 20:31:27 +01:00
• 308c93ac81 docs: reject runs with extra skills outright (addr Codex #25 P2) Jesse ZhangandClaude Opus 4.8 2026-06-24 20:25:08 +01:00
• 5cd30bac2b docs: require running the harness as it ships (no extra skills) Jesse ZhangandClaude Opus 4.8 2026-06-24 20:18:08 +01:00
• eaf2737ecc ci: verify data to site auto-deploy dispatch Jesse ZhangandClaude Opus 4.8 2026-06-21 12:47:59 +01:00
• fa56bfe524 Add DeepSeek V4 Flash (Reasonix · Max) skeleton-watch run (#21) 6bcj 2026-06-21 19:31:36 +08:00
• 1605c5e20b ci: trigger run to verify registry auto-sync workflow Jesse ZhangandClaude Opus 4.8 2026-06-21 11:32:30 +01:00
• 30983f0e7d Add AGENTS.md + tighten contribution flow Jesse ZhangandClaude Opus 4.8 2026-06-21 11:29:23 +01:00
• 2fb8499fa8 Add GPT-5.4 (Codex CLI · xhigh) skeleton-watch run (#22) YinLing 2026-06-21 06:19:43 -04:00
• 75b18a76e4 Add skeleton-watch runs: DeepSeek-V4-Pro, Gemini 3.1/3.5, GLM-5.2, Kimi K2.7, MiMo (#23) OHCJ099 2026-06-21 18:19:25 +08:00
• c9cf217db3 Update registry: GLM-5.1 now ran (ZCode · Max, pelican-cycling) Jesse ZhangandClaude Opus 4.8 2026-06-20 09:17:15 +01:00
• 06b9415b8d Add GLM-5.1 (ZCode · Max) pelican-cycling SVG Dmt3tian 2026-06-20 16:16:43 +08:00
• 8fb741ceec Add GPT-5.5 (Codex CLI xhigh) skeleton-watch run Jesse ZhangandClaude Opus 4.8 2026-06-19 01:20:28 +01:00
• 50a2607db3 Disable GPT-5.5 Pro skeleton-watch bloom entirely for eye safety Jesse ZhangandClaude Opus 4.8 2026-06-19 01:09:47 +01:00
• 16f528892c Tame GPT-5.5 Pro skeleton-watch blinding bloom glow Jesse ZhangandClaude Opus 4.8 2026-06-19 01:01:18 +01:00
• 2cbe8b457f Document Opus 4.7 skeleton-watch exploded-view bug in run note Jesse ZhangandClaude Opus 4.8 2026-06-19 00:54:59 +01:00
• 6b5c5aba25 Fix GPT-5.5 Pro skeleton-watch mainspring crash (fractional tube segments) Jesse ZhangandClaude Opus 4.8 2026-06-19 00:50:11 +01:00
• 7eaac09dc0 Sort models by version desc and clarify effort belongs to the model (#18) Jesse ZhangandClaude Opus 4.8 2026-06-18 23:48:13 +01:00
• 3d5bf6967c Normalize artifact filenames and register new runs (#17) Jesse ZhangandClaude Opus 4.8 2026-06-18 23:36:38 +01:00
• dd67d6fda5 Add Step 3.7 Flash runs (mythos-craft, pelican-cycling) Jesse ZhangandClaude Opus 4.8 2026-06-18 22:03:52 +01:00
• 13da28bd8e Add MiMo v2.5 Pro UltraSpeed runs (mythos-craft, pelican-cycling) OHCJ099 2026-06-17 03:20:34 +08:00
• b07823f4be Fix GLM-5.2 mythos startup Nagi-ovoandCodex 2026-06-14 23:53:18 +01:00
• f9a44ec74e Fix GLM-5 Turbo mythos startup Nagi-ovoandCodex 2026-06-14 23:48:10 +01:00
• 2bcb1409c4 Update registry for GLM-5 Turbo variant Nagi-ovoandCodex 2026-06-14 23:31:20 +01:00
• ce906b7f02 Add GLM-5 Turbo mythos variant Nagi-ovoandCodex 2026-06-14 23:30:53 +01:00
• 9f899eaeba Add GLM-5 Turbo mythos artifact Nagi-ovoandCodex 2026-06-14 22:54:20 +01:00
• 08f2fb4b7d Add GLM-5 Turbo pelican artifact Nagi-ovoandCodex 2026-06-14 22:49:09 +01:00
• bfeba2bfbd Add GLM-5.2 pelican artifacts Nagi-ovoandCodex 2026-06-14 22:26:12 +01:00
• 2b85907eb3 Add Claude Haiku 4.5 artifacts Nagi-ovoandCodex 2026-06-14 06:54:22 +01:00
• 00226c3e70 Add Claude Sonnet 4.6 pelican variants Nagi-ovoandCodex 2026-06-14 06:30:44 +01:00
• c0d9952c28 Add Gemini 3.1 Pro Cursor pelican artifact Nagi-ovoandCodex 2026-06-14 01:32:04 +01:00
• ac63b84938 Add GPT-5.4 Codex mythos artifact Nagi-ovoandCodex 2026-06-14 01:20:59 +01:00
• 508d601dd3 Add MiniMax M2.7 pelican artifact Nagi-ovoandCodex 2026-06-14 01:16:44 +01:00
• 6db97658b2 Generate registry tables from data Nagi-ovoandCodex 2026-06-14 01:11:56 +01:00
• a7b5d09658 Add M3 and K2.7 pelican variants Nagi-ovoandCodex 2026-06-14 01:06:12 +01:00
• f5d1f373c5 Add GPT-5.4 Codex pelican variants Nagi-ovoandCodex 2026-06-14 01:01:49 +01:00
• 4ceb49d8e1 Add Claude Sonnet 4.6 pelican artifact Nagi-ovoandCodex 2026-06-14 00:57:37 +01:00
• f2208a562d Add Grok 4.3 pelican artifact Nagi-ovoandCodex 2026-06-14 00:42:47 +01:00
• 9391a32015 Clarify Cursor CLI provenance Nagi-ovoandCodex 2026-06-14 00:35:10 +01:00
• 4a5aad4a35 Add new Cursor artifacts Nagi-ovoandCodex 2026-06-14 00:28:24 +01:00
• 7a1571f46b Remove empty artifacts from Cursor runs Jesse Zhang 2026-06-14 00:16:49 +01:00
• cb79f09c88 Fix Cursor run contributor handles Jesse Zhang 2026-06-13 20:52:31 +01:00
• 3936cd26af Add Cursor runs for Claude and Gemini models Jesse Zhang 2026-06-13 19:24:46 +01:00
• 9bc21c2ace Add GLM-5.2 as a pending model Jesse ZhangandClaude Opus 4.8 2026-06-13 14:43:15 +01:00
• 8ece6b8941 README: Kimi K2.7-Code now 02 runs (mythos-craft added via #11) Jesse ZhangandClaude Opus 4.8 2026-06-13 14:32:18 +01:00
• b6b60b6e1e feat: add Kimi K2.7-Code mythos-craft run (#11) 4 people 2026-06-13 21:31:27 +08:00
• a12017f31e Reorganize artifacts by model and harness Jesse Zhang 2026-06-13 12:59:01 +01:00
• 4027ba94c2 README: add Kimi K2.7-Code row to both registry tables Jesse ZhangandClaude Opus 4.8 2026-06-13 11:59:00 +01:00