Model Comparison
Kimi K3 vs Claude Sonnet 5
Kimi K3 (max) leads Claude Sonnet 5 (max effort) by 344 Elo, and their 95% ranges sit 254 Elo apart. Even Kimi K3's lowest-rated configuration, Kimi K3 (high), ranks above Claude Sonnet 5 (max effort). Among 78 models, each ranked by its best configuration, Kimi K3 is #10 and Claude Sonnet 5 is #23. Cost per script: $0.362 for Kimi K3 (max) and $0.696 for Claude Sonnet 5 (max effort).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickKimi K3
Kimi K3 (high)
Pick Kimi K3 (high) for day-to-day scripts, since it costs about what Sonnet charges at high, $0.128 a script, and ranks 326 Elo above it.
PickClaude Sonnet 5
Claude Sonnet 5 (max effort)
Pick Claude Sonnet 5 (max effort) for a script with a hard length target, the one metric where it edges Kimi K3 (max), at $0.696 a script.
Kimi K3 wins this at every setting, and mostly for less money. Kimi K3 (max) leads Claude Sonnet 5 (max effort) by 344 Elo, with 95% ranges far apart, and by best setting that's the #10 model of 78 against the #23 model. The cheaper comparison is even more lopsided. Kimi K3 (high) costs $0.128 a script and still beats Sonnet's max effort by 119 Elo with separate ranges, while Sonnet charges $0.696, more than five times as much, and takes twelve minutes. At high on both sides, the price is nearly the same and Kimi leads by 326 Elo. Both models gain a lot from thinking, Kimi 225 Elo from high to max and Sonnet 207, and Sonnet pays almost six times its high price for the step where Kimi pays less than three. Sonnet's one edge is length adherence at max effort, a little over two points above Kimi at max. Its drafts also vary more from one run to the next at both settings. For most work, Kimi at high is enough for me, and I'd move to max for anything I publish.
Disclosure: Claude Sonnet 5 comes from the same lab as one of the four judges, Claude Opus 5.5. The other three sit outside its lab, so it is never scored by its own lab alone (how the panel works). The judge analysis measures how much each judge favors its own lab.
How to Read the Writing Score, Writing Elo and 95% Ranges
Writing Score and Writing Elo. The Writing Score (0 to 100) is the weighted average of the nine metric scores: seven from the judges, Length Adherence from code and the Slop Score half from each. The Writing Elo is a rating from pairwise comparisons: on each script, each configuration's average across its drafts is compared with every other configuration's, and gaps within the draft-to-draft variation count as draws. Elo rewards winning often, so the two can put configurations in a different order.
Elo ranges. Each 95% range shows how far a configuration's Elo could move if the drafts had come out slightly differently. It comes from resampling every configuration's recorded draft scores on each reference script and ranking again. Comparing two separate ranges does not test the Elo gap between them: ranges far apart are strong evidence for the order, and overlapping ranges do not mean a tie. The reference scripts stay fixed, so the ranges say nothing about new scripts. The methodology page has the full description.
All Thinking Levels of Both Models
Every ranked configuration of Kimi K3 and Claude Sonnet 5, scored on the same 10 scripts by the same four judges.
- Each row is one configuration: the model at one thinking level. The dot is its Writing Elo, a rating from pairwise comparisons of the scores on each script, and the bar is its 95% range: how far that Elo could move if the drafts had come out slightly differently.
- When two bars overlap, the board cannot order those two configurations. Bars far apart are strong evidence for the order.
- The table under the chart lists the same configurations in the same order and adds the Writing Score (the 0 to 100 consensus of the judges and code), cost, time and configuration rank (the place among all configurations on the board).
Shaded rows are the configurations chosen for the metric comparison below.
| Configuration | Writing Elo | 95% Range | Writing Score | Cost / Script | Time / Script | Reasoning Tokens | Configuration Rank |
|---|---|---|---|---|---|---|---|
| Kimi K3 (max) | 2203 | 2158 to 2243 | 82.2 | $0.362 | 9.9 min | 18,568 | #20 |
| Kimi K3 (high) | 1978 | 1936 to 2029 | 80.3 | $0.128 | 2.8 min | 3,081 | #37 |
| Claude Sonnet 5 (max effort) | 1859 | 1812 to 1904 | 79.2 | $0.696 | 12.0 min | N/A | #45 |
| Claude Sonnet 5 (high) | 1652 | 1602 to 1703 | 76.6 | $0.121 | 1.9 min | N/A | #58 |
Cost is one script at the API list price of the route used, uncached and without judging. Time is the average for one accepted script, retries included. N/A under Reasoning Tokens means the board has no separate reasoning count for that route.
Computed Findings Across Thinking Levels
Each finding is computed from the configurations above. Where two 95% ranges overlap, the board cannot order those two configurations.
- Best Configurations Head to Head. Kimi K3 (max) leads Claude Sonnet 5 (max effort) by 344 Elo, and their 95% ranges do not overlap (2158 to 2243 against 1812 to 1904), which is strong evidence for that order.
- Every Kimi K3 Configuration Ranks Higher. Both Kimi K3 configurations rank above both Claude Sonnet 5 configurations: the lowest-rated, Kimi K3 (high) at Elo 1978, still beats Claude Sonnet 5 (max effort) at Elo 1859. Their 95% ranges do not overlap.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, Kimi K3 (high) at Elo 1978 and $0.128 per script leads Claude Sonnet 5 (high) at Elo 1652 and $0.121 per script by 326 Elo. Their 95% ranges do not overlap.
- Same Level Name, Side by Side. Kimi K3 has the higher Writing Elo at every level name both models use: high and max. The 95% ranges do not overlap at any of them. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Cheapest Kimi K3 Configuration Above Claude Sonnet 5's Best. The cheapest Kimi K3 configuration with a higher Writing Elo than Claude Sonnet 5 (max effort), at Elo 1859 and $0.696 per script, is Kimi K3 (high), at Elo 1978 and $0.128 per script. It costs less than the configuration it beats.
- Lowest to Highest Thinking Level. Kimi K3 moves +225 Elo from high to max, at about 2.8 times the cost per script. Claude Sonnet 5 moves +207 Elo from high to max effort, at about 5.8 times the cost per script.
Writing Elo at Each Shared Level Name
| Level | Kimi K3 | Claude Sonnet 5 | Gap | 95% Ranges |
|---|---|---|---|---|
| high | 1978 | 1652 | +326 | Separate |
| max | 2203 | 1859 | +344 | Separate |
Gap is Kimi K3 minus Claude Sonnet 5 at the same level name, using each model's highest-rated configuration at that level.
Two Chosen Configurations Compared
Pick one configuration of each model to compare their metric scores, consistency across drafts and per-script scores. Each menu starts on the model's best configuration.
Scores by Metric
Kimi K3 (max) scores higher on eight of the nine metrics and Claude Sonnet 5 (max effort) on one. Weighted by each metric's share of the Writing Score, Hook Strength does the most to put Kimi K3 (max) ahead, with a 7.6-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Kimi K3 (max) | Claude Sonnet 5 (max effort) | |
|---|---|---|
| Score spread across drafts (±) | 1.68 | 2.39 |
| Lowest script score | 80.0 Script 10 | 75.7 Script 4 |
| Highest script score | 83.8 Script 9 | 81.5 Script 9 |
| Range across scripts | 3.8 | 5.8 |
Spread is how much the Writing Score moves between a configuration's drafts, and lower is steadier. Green marks the better number in each row.
Scores by Script
Writing Score on each reference script. Gap is Kimi K3 (max) minus Claude Sonnet 5 (max effort), and the higher score is in bold.
| Script | Kimi K3 (max) | Claude Sonnet 5 (max effort) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.4 | 77.4 | +4.0 |
| Script 2 news-analysis / skeptical explainer | 82.6 | 78.9 | +3.7 |
| Script 3 personal roadmap / opinion | 81.8 | 78.1 | +3.7 |
| Script 4 short explainer | 80.1 | 75.7 | +4.4 |
| Script 5 news-analysis / opinion explainer | 83.4 | 80.9 | +2.5 |
| Script 6 founder announcement / personal origin story | 83.2 | 81.1 | +2.1 |
| Script 7 personal technical walkthrough / agentic workflow case study | 83.6 | 81.2 | +2.4 |
| Script 8 product release announcement / personal observation | 82.3 | 79.3 | +3.0 |
| Script 9 career guide / hiring analysis | 83.8 | 81.5 | +2.3 |
| Script 10 engineering process walkthrough / presentation adaptation | 80.0 | 78.0 | +2.0 |
Scorecards and Thinking Pages
Each configuration name in the table above opens its own scorecard.
Compare With Another Model
Pick a second model. A pair with its own written match-up opens that page, and any other pair opens in the comparison tool.
Nearby Match-Ups by Best Writing Elo
Every configuration wrote five drafts for each of the same 10 briefs, from the same prompt. Generation was closed-book, with the prompt as the only source and no web search or other tools. Each judge scores every draft once: Claude 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, a typed judge from TypeSafe that answers each metric as a multiple-choice question. The channel's finished script is their reference for the voice, and it gets no score on the board itself.
← All comparisons