Model Comparison
Claude Sonnet 5.5 (max effort) leads Kimi K3.1 Pro (max) by 346 Elo, and their 95% ranges sit 246 Elo apart. Among 87 models, each ranked by its best configuration, Claude Sonnet 5.5 is #3 and Kimi K3.1 Pro is #9. Cost per script: $1.38 for Claude Sonnet 5.5 (max effort) and $0.251 for Kimi K3.1 Pro (max).
Last updated , from board data generated at 17:52 UTC.
PickClaude Sonnet 5.5
Claude Sonnet 5.5 (xhigh)
Pick Claude Sonnet 5.5 (xhigh) over Kimi K3.1 Pro (max), since it ranks 112 Elo higher with separate ranges, finishes faster and costs $0.302 a script.
PickKimi K3.1 Pro
Kimi K3.1 Pro (max)
Pick Kimi K3.1 Pro (max) over Claude Sonnet 5.5 (high) when visual cues matter, since it leads that setting by 194 Elo and almost ten points on visual cues, for $0.251 a script.
Kimi K3.1 Pro lands between two Claude Sonnet 5.5 settings, and the one above it barely costs more. Claude Sonnet 5.5 (xhigh) sits 112 Elo above Kimi K3.1 Pro (max) with separate 95% ranges, for $0.302 a script against $0.251, and it finishes in 3.1 minutes where Kimi takes 5.5. Drop Sonnet to high and Kimi wins clearly, 194 Elo up with ranges apart, though Sonnet at high costs $0.092 and takes a minute. Sonnet's thinking level decides everything here, with 766 Elo between low and max effort, while Kimi has only its max row. At the top, Claude Sonnet 5.5 (max effort) leads Kimi by 346 Elo and wins all ten scripts, the #3 model of 87 against the #9 model, at $1.38 and over fourteen minutes. Against xhigh, Sonnet leads on craft by about three points and on tone by two and a half. Kimi keeps better visual cues, by almost five points, stronger hooks and a bit more substance. For me, Sonnet at xhigh is the pick here: the better writing for a few cents more, and faster.
Disclosure: Claude Sonnet 5.5 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.
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.
Every ranked configuration of Claude Sonnet 5.5 and Kimi K3.1 Pro, scored on the same 10 scripts by the same four judges.
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 |
|---|---|---|---|---|---|---|---|
| Claude Sonnet 5.5 (max effort) | 2496 | 2435 to 2539 | 84.6 | $1.38 | 14.3 min | N/A | #6 |
| Claude Sonnet 5.5 (xhigh) | 2262 | 2215 to 2299 | 83.2 | $0.302 | 3.1 min | N/A | #15 |
| Kimi K3.1 Pro (max) | 2150 | 2104 to 2189 | 82.5 | $0.251 | 5.5 min | 19,487 | #19 |
| Claude Sonnet 5.5 (high) | 1956 | 1908 to 1996 | 81.0 | $0.092 | 1.0 min | N/A | #35 |
| Claude Sonnet 5.5 (medium) | 1776 | 1734 to 1816 | 79.4 | $0.065 | 0.6 min | N/A | #62 |
| Claude Sonnet 5.5 (low) | 1730 | 1695 to 1765 | 78.9 | $0.061 | 0.7 min | N/A | #66 |
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.
Each finding is computed from the configurations above. The 95% ranges describe individual configurations; overlap alone establishes neither a tie nor an order for a pair.
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.
Claude Sonnet 5.5 (max effort) scores higher on six of the nine metrics and Kimi K3.1 Pro (max) on three. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put Claude Sonnet 5.5 (max effort) ahead, with a 3.5-point lead on that metric. The weight beside each metric is its share of the Writing Score.
| Claude Sonnet 5.5 (max effort) | Kimi K3.1 Pro (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.22 | 1.65 |
| Lowest script score | 83.0 Script 10 | 80.4 Script 7 |
| Highest script score | 86.7 Script 9 | 85.5 Script 9 |
| Range across scripts | 3.7 | 5.1 |
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.
Writing Score on each reference script. Gap is Claude Sonnet 5.5 (max effort) minus Kimi K3.1 Pro (max), and the higher score is in bold.
| Script | Claude Sonnet 5.5 (max effort) | Kimi K3.1 Pro (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 84.2 | 81.3 | +2.9 |
| Script 2 news-analysis / skeptical explainer | 84.8 | 83.2 | +1.6 |
| Script 3 personal roadmap / opinion | 84.0 | 81.9 | +2.1 |
| Script 4 short explainer | 85.0 | 82.0 | +3.0 |
| Script 5 news-analysis / opinion explainer | 84.8 | 84.2 | +0.6 |
| Script 6 founder announcement / personal origin story | 84.6 | 83.0 | +1.6 |
| Script 7 personal technical walkthrough / agentic workflow case study | 85.0 | 80.4 | +4.6 |
| Script 8 product release announcement / personal observation | 83.9 | 82.1 | +1.8 |
| Script 9 career guide / hiring analysis | 86.7 | 85.5 | +1.2 |
| Script 10 engineering process walkthrough / presentation adaptation | 83.0 | 81.3 | +1.7 |
Each configuration name in the table above opens its own scorecard.
Pick a second model. A pair with its own written match-up opens that page, and any other pair opens in the comparison tool.
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