Lab Comparison
Last updated , from board data generated at 17:52 UTC.
All 3 ranked Thinking Machines configurations on ToneBench, side by side: Writing Elo, Writing Score, the nine metrics, and cost and time per script. A configuration is one model at one thinking level.
Ranks in these notes are configuration ranks: each setting's place among all 151 configurations. The Highest Writing Elo card above gives the model rank.
Picks and Notes From Louis
For scripts you'll publish, I'd use Inkling 2 Small (xhigh), at $0.026 and about 2.2 minutes per script. It's 32 Elo ahead of Inkling 2 Small (high), and their ranges overlap, though overlap alone doesn't say which one writes better. But at xhigh the scripts land much closer to the target length, and that's worth about a cent more a script to me. If you want lots of drafts back fast, Inkling 2 Small (high) is the cheapest and fastest row here, at $0.016 and 1.2 minutes.
I'd only keep Inkling (high) if you need weights you can run yourself today. It's the priciest row in the family, and it sits far below both Inkling 2 Small settings.
As good as that jump is, though, Inkling 2 Small isn't the best cheap writer on the board. DeepSeek V4.1 Flash 1017 (high) ranks far above both of its settings, at #34, for less money, and its weights are already out.
Thinking Machines has 2 models on the board, and the jump from the first to the second is the story here. Its first model, Inkling, has open weights, and Inkling (high) on Together sits down at #122. Inkling 2 Small (xhigh) lands at #67, 733 Elo higher, and both Inkling 2 Small settings cost less per script than Inkling's $0.042. Better and cheaper at once doesn't happen often. The catch is access. For now, only Thinking Machines' own Tinker platform serves Inkling 2 Small, and its weights aren't out yet. Thinking Machines says they'll follow after outside safety testing, so until then the board counts it as closed.
Every row wrote the same 10 scripts for the same four blind judges, so these Writing Elo ratings sit on the leaderboard's scale. The rank column is the configuration rank, each setting's place among all 151 configurations on the board. Rows are grouped by model: a highlighted row is a model's best configuration, and the rows under it are the same model at other thinking levels. The ± after each Elo is half the width of its 95% range, and scores run from 0 to 100. Cost is one full script at the API list price of the route used. Each name opens its scorecard, and the head-to-head comparisons cover models from different labs.
With the metric scores shown, the table scrolls sideways.
| Configuration Rank | Configuration | Writing Elo | Writing Score | Cost / Script | Time / Script | Tone & Voice Match | Writing Craft & Clarity | Substance, Accuracy & Value | Hook Strength | YouTube Best Practices | Continuity & Emotion | Slop Score | Length Adherence | Visual Cue Quality |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| #67 | Inkling 2 Small (xhigh) | 1728 ±43 | 78.9 | $0.026 | 2.2 min | 75.8 | 75.7 | 81.8 | 80.3 | 77.2 | 77.5 | 81.3 | 90.7 | 73.4 |
| #68 | Inkling 2 Small (high) | 1696 ±55 | 78.1 | $0.016 | 1.2 min | 75.7 | 76.0 | 81.3 | 80.0 | 77.1 | 77.5 | 81.1 | 82.5 | 72.4 |
| #122 | Inkling (high) · open weights | 995 ±82 | 68.8 | $0.042 | 1.3 min | 65.9 | 66.3 | 73.4 | 72.7 | 68.5 | 69.1 | 66.6 | 66.4 | 70.1 |
Only Inkling 2 Small ran at more than one thinking level here. Its page shows how the score, cost and time change from one level to the next.
Each comparison lists every thinking level of both models, with Writing Elo, cost and time side by side. The line under each pair gives the Writing Elo gap between the two best configurations. A pair outside the written match-ups opens in the comparison tool.
← All comparisons