Spaces:
Running
Running
Commit History
Yesterday
-
Text-to-Scene: add Gemini 4 Hydrogen (xhigh)
Verified signature64f7a29
3 days ago
-
Text-to-Scene: Claude Fable 5.2 (max) cost
Verified signature21ada47 -
Text-to-Scene: add Claude Fable 5.2 (max)
Verified signature17e9a72 -
Text-to-Scene: add Inkling 2 Small (max)
Verified signature312c93d -
Text-to-Scene: add Gemini 4 Carbon (high)
Verified signaturea549a72
5 days ago
-
Text-to-Scene: Muse Ember 1.0 (max) cost
Verified signaturea8da785 -
Text-to-Scene: add Muse Ember 1.0 (max)
Verified signature2439475
9 days ago
-
Text-to-Scene: mark Kimi K3.1 Pro (max) as open weights
Verified signature140fa10 -
Text-to-Scene: add Hy4 (max)
Verified signature81c94d2
18 days ago
-
Text-to-Scene: add GPT-6.1 Terra (max)
Verified signature840e436
20 days ago
-
Text-to-Scene: add Kimi K3 (max)
Verified signature93abd01 -
Text-to-Scene: update Kimi K3.1 Pro (max) (4 cases rerun)
Verified signature2f2e33f -
Text-to-Scene: add Muse Wonder 1.0 (max)
Verified signaturecebd676
21 days ago
-
Text-to-Scene: add cost for Kimi K3.1 Pro (max)
Verified signatureb876105
24 days ago
-
Text-to-Scene: add Qwen3.8 27B (thinking on)
Verified signature1e1f598
26 days ago
-
Text-to-Scene: update DeepSeek V4.1 Flash 1017 results
Verified signatureff58826 -
Text-to-Scene: add GPT-5.6 Luna (max)
Verified signature6031d7c -
Text-to-Scene: add GPT-5.6 Terra (max)
Verified signatureef6feef
27 days ago
-
Text-to-Scene: add DeepSeek V4.1 Flash 1017 (max)
Verified signaturebdf75eb -
Text-to-Scene: add Qwen3.8 27B (thinking off)
Verified signaturedbd010c -
Text-to-Scene: add Step 5 Preview (max)
Verified signature17d0c97
28 days ago
-
Text-to-Scene: corrected scores for 7 models (re-scoring; Grok 4.7 and Muse Spark 1.3 re-runs), add Gemma 4 31B (thinking off) and Nemotron 3.5 Super VL
Verified signature973e4c6
29 days ago
-
Text-to-Scene: Gemma 4 31B (thinking on) cost estimated from its logged tokens
Verified signatureGemma 4 31B ran on self-hosted weights, so nothing was billed. Its cost is now the token counts its agent logged on every model call (scripts/t2s_token_cost.py) at Gemma 4 31B's OpenRouter list price ($0.20 input, $0.40 output per million): median $0.056 per case, shown as $0.06*, with the basis in the table, tooltips, Pareto caption and gallery. It now has a Pareto point, on the frontier. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>391a498 -
Text-to-Scene: four more finished runs (19 configurations); Xiaomi mark; open-weights tags
Verified signatureSnapshot 2026-10-16 16:01 UTC of the internal leaderboard: GPT-6 Luna (max), Muse Spark Open (max), MiMo V2.6 Pro (max) and Gemma 4 31B (thinking on) have all 20 cases scored and join the bars, Pareto, ranking, tooltips and gallery (19 configurations); Inkling has not finished and stays out. Xiaomi gets its own mark (Simple Icons) and the internal leaderboard's amber; Muse Spark Open and MiMo V2.6 Pro are tagged open weights (OpenRouter lists their Hugging Face weights). Gemma 4 31B ran on self-hosted weights, so it has no billed cost and no Pareto point, and the pages say so. Scores never rounded up; median cost per case. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>0c7052b -
Text-to-Scene: Muse Wonder Full 1.0 cost from its CLI's own token logs
Verified signatureThe harness stream of the muse CLI has no usage, so the internal table left Muse Wonder Full without a cost. The CLI's own session logs record every model call's provider token counts (they match its cost ledger); scripts/t2s_muse_cost.py prices them at Muse Wonder's OpenRouter list rate ($4 input, $0.20 cached input, $20 output per million; Wonder Full is sold by subscription), with the CLI's background model Muse Spark 1.3 at its own rate: median $3.66 per case. The skill-reminder side calls are not logged readably and are left out. Ranking, Pareto, tooltips and gallery updated; the pages say how this cost is derived. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>b85bdcb -
Text-to-Scene: the October 2026 re-run replaces the paper's Research Track numbers; latest cases; gallery
Verified signatureLeaderboard (Text-to-Scene tab): bars, Pareto, ranking and tooltips from the internal leaderboard's sandboxed re-run, only configurations with all 20 cases scored; scores never rounded up, median cost per case. Cases: the four-agent comparison videos with a scene picker; the Industrial Harbor showcase stays. Gallery: every shown configuration on all 20 scenes, by agent and by scene. Image-to-Scene, the Task Format example, the Takeaways and the case explorer keep the paper's evaluation. Rebuild: scripts/t2s_sandbox_round.py and scripts/t2s_gallery.py (see README). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>988be21
-
Rebuild reference Pareto frontier and default all case displays to live 3D
5c0856a