Model Scorecard
Kimi K3 (max)
Moonshot (Kimi) · open weights
Kimi K3 ranks #12 of 87 models on the November 2026 ToneBench board, and Kimi K3 (max) is its best configuration, #26 of 151 configurations, with a Writing Score of 82.2/100 and a Writing Elo of 2116. One script costs $0.362 at API list price.
Last updated , from board data generated at 17:52 UTC.
Rank, scores, the nine metrics, the 10 reference scripts, cost and setup for one configuration (a model at one reasoning setting). Key Results sums it up; the section links below it jump to the detail.
Key Results
- StandingKimi K3 ranks #12 of 87 models, and this is its best configuration. As a configuration, it is #26 of 151 configurations by Writing Elo (2116), in the upper third of the board. Its 95% range (2076 to 2152) overlaps 12 other configurations, ranked #17 to #29.
- MetricsBest-ranked: Hook Strength (83.1, 13th of 151 configurations, +3.5 against the board median). Lowest-ranked: Substance, Accuracy & Value (83.5, 55th of 151 configurations, +1.7 against the board median).
- ScriptsFrom 80.0 on Script 10 (engineering process walkthrough) to 83.8 on Script 9 (career guide): a 3.8-point spread across the 10 reference scripts.
- ConsistencyIts Writing Score moves ± 1.7 between drafts of the same script, against ± 2.5 for the median configuration: steadier than most.
- ValueGPT-6 Sol (medium) ranks higher with an overlapping Elo range and costs about $0.056 per script, against $0.362 per script for this one.
Louis's PickOf the two Kimi K3 settings, this is the one I'd use. If you're not tied to Kimi K3, Claude Opus 5.5 (high) ranks clearly higher for no more per script.
More Context Behind These Results
Writing Elo comes from comparing its average on each script with every other configuration's average on that same script; a gap smaller than the draft-to-draft variation counts as a draw (what the ranges can and cannot show).
On Hook Strength, its best-ranked metric, the judges rated its openings above the typical configuration's. Even its lowest-ranked metric, Substance, Accuracy & Value, ranks in the top half of the board, so no metric stands out as a weak spot.
The script format moves its score. If most of your scripts look like its best or weakest format, that result is a better guide than the average.
Its drafts vary little, so the first draft is usually close to the next one.
It outranks 7 configurations that cost at least 50% more.
Among open-weight models, Kimi K3 is 2nd of 34. As a configuration, it is 2nd of 43 open-weight configurations. That is one of the strongest open-weight results on this board.
All Settings of Kimi K3
Kimi K3 is also on the board at other effort settings, and none of them rank above this one. The thinking-level page for Kimi K3 charts how quality, cost and time change with the setting.
| Setting | Configuration Rank | Writing Score | Writing Elo | Cost / Script | Time / Script |
|---|---|---|---|---|---|
| max this page | #26 | 82.2 | 2116 | $0.362 | 9.9 min |
| high | #45 | 80.3 | 1891 | $0.128 | 2.8 min |
Skill Profile Across the Nine Metrics
Each corner is one metric on a 0 to 100 scale; the further out, the higher the score. A corner outside the dashed line beats the board median. Hover or tap a point for its exact score, and a metric name for what it rewards.
Scores by Metric
Nine metrics, each scored 0 to 100 and weighted into the Writing Score; the weight sits under each name. Rank is out of all 151 ranked configurations.
Scores by Reference Script
Every ranked configuration writes five drafts for each of the same 10 briefs, and each score is the mean of those drafts. The rank and board median compare it with every configuration on that script, which separates a weak result from a hard script. The result on the format closest to your own work is the most relevant.
Consistency Between Drafts
Every score on this page is the mean of 5 drafts per script. The ± is the standard deviation between those drafts: the larger it is, the more two drafts of the same script can differ.
Compared with the typical model, it's steadiest on Tone & Voice Match: ± 1.0 between drafts against ± 1.9.
Consistency by Metric
| Metric | This model | Board median | Verdict |
|---|---|---|---|
| Tone & Voice Match ? | 78.7 ± 1.0 | ± 1.9 | steadier than most |
| Writing Craft & Clarity ? | 78.8 ± 0.9 | ± 1.5 | typical |
| Substance, Accuracy & Value ? | 83.5 ± 1.8 | ± 2.1 | typical |
| Continuity & Emotion ? | 82.3 ± 1.1 | ± 1.5 | typical |
| YouTube Best Practices ? | 81.2 ± 2.7 | ± 2.4 | typical |
| Hook Strength ? | 83.1 ± 2.2 | ± 2.7 | typical |
| Length Adherence ? | 94.2 ± 4.8 | ± 6.6 | typical |
| Slop Score ? | 83.4 ± 1.3 | ± 1.6 | typical |
| Visual Cue Quality ? | 80.0 ± 2.4 | ± 2.9 | typical |
Cost, Time and Tokens per Script
Logged on every run; none of these figures affects the Writing Score. Time is the average time to one accepted script, retries included. Cost is one script at the API list price.
Scores by Judge
Four judges score the same 50 stored drafts blind against the same rubric: three LLM judges from three labs, plus Jev, a typed judge from TypeSafe that rates each metric on five described quality levels. No single judge's taste decides the result. The Writing Score of 82.2 combines their scores with the parts computed in code (Length Adherence and half of the Slop Score). The highest and lowest judge are 12.0 points apart on its Writing Score. That is close to the board median of 13.4. Each judge also has its own scale, so every card shows that judge's score against its average across the board. How the panel works.
Evaluation Setup
How this exact configuration was run and judged: route, model ID, dates, sampling and prompt.
- Accessed viaOpenRouter · model page ↗.
- Exact model / route id
moonshotai/kimi-k3(the request sets no level; the provider applies max). - Generations5 independent runs × 10 scripts = 50 drafts, stored after generation and never edited.
- Run dates2026-10-08.
- JudgesClaude Opus 5.5 at medium effort through the Claude Code subscription, GPT-6.1 Sol at medium reasoning through the Codex CLI, GLM 5.3 Flash through OpenRouter, and Jev 1.13 from TypeSafe. One call per judge per draft. All four score every draft on their own, blind to which model wrote it. The three LLM judges use the identical rubric and have to quote evidence before they score a metric. Jev answers the same rubric as one question per metric, choosing among five described quality levels, and writes no text. Seven metrics are the plain average of the four judges. Length is computed from the spoken word count, and Slop is half computed (lexical scans minus the spoken-dash penalty) and half judged. The Writing Elo is cross-checked with a Bradley-Terry fit of the same pairwise results (methodology).
- Sampling and promptThe provider's default sampling, with no fine-tuning and no system-prompt changes. Every current-ranked model gets the same prompt, about 13,000 tokens (the count shifts a bit with each model's tokenizer): a style guide built from Louis's voice and storytelling guides, the target length, and the brief with its research packet. Generation is closed-book on every route: the prompt is the only source, with no web search, browsing, code execution, file access or other tool (generation).
- What stays privateThe exact rubric and any non-public reference material. Each script is normally benchmarked before its video is published, which lowers the odds that a model has seen the reference, though it does not rule it out (why).
Frequently Asked Questions
How Good Is Kimi K3 (max) at Writing?
Kimi K3 ranks #12 of 87 models on ToneBench, and this is its best configuration. This configuration is #26 of 151 configurations, in the upper third of the board, with a Writing Elo of 2116 and a Writing Score of 82.2/100. The ranks come from full YouTube scripts written in the voice of Louis-François Bouchard and judged blind, with the channel's finished script as the reference. The benchmark measures long-form scripted writing, so the result does not carry over to every kind of text.
Is Kimi K3 (max) the Best Moonshot (Kimi) Model for Writing?
Not quite. Kimi K3 is 2nd of 3 Moonshot (Kimi) models. The top one is Kimi K3.1 Pro, through Kimi K3.1 Pro (max), about 34 Elo ahead of this setting, inside the overlap of their Elo ranges.
Is Kimi K3 (max) Good Value for the Money?
It costs about $0.362 per script. GPT-6 Sol (medium) ranks higher with an overlapping Elo range and costs less.
What Are the Strengths and Weaknesses of Kimi K3 (max)?
Its best-ranked metric is Hook Strength (83.1, 13th of 151 configurations, +3.5 against the board median), and its lowest-ranked is Substance, Accuracy & Value (83.5, 55th of 151, +1.7). Even that one ranks in the top half of the board. The Scores by Metric section shows the board median and the board's best for each one.
How Was Kimi K3 (max) Evaluated?
It was run through OpenRouter, with the exact model/route ID moonshotai/kimi-k3, first run on 2026-10-08. It wrote each script 5 times with the provider's default sampling and no fine-tuning. The Evaluation Setup section and the methodology page have the details.
Does Kimi K3 (max) Have Open Weights?
Yes. Its weights are public, so it can be downloaded and run on your own hardware. Check the license if you need open source in the strict sense. Among open-weight configurations it is 2nd of 43 for writing.