Model Comparison
Kimi K3.1 Pro vs GPT-6.1 Terra
Kimi K3.1 Pro (max) leads GPT-6.1 Terra (max) by 268 Elo, and their 95% ranges sit 189 Elo apart. Among 84 models, each ranked by its best configuration, Kimi K3.1 Pro is #8 and GPT-6.1 Terra is #23. Cost per script: $0.251 for Kimi K3.1 Pro (max) and $0.079 for GPT-6.1 Terra (max).
Last updated , from board data generated at 20:15 UTC.
Picks and Verdict
PickKimi K3.1 Pro
Kimi K3.1 Pro (max)
Pick Kimi K3.1 Pro (max) for anything you film, since it leads Terra's best by 268 Elo with separate ranges and wins all ten scripts at $0.251.
PickGPT-6.1 Terra
GPT-6.1 Terra (low)
Pick GPT-6.1 Terra (low) for quick, cheap drafts at $0.027 and 0.5 minutes a script, with cleaner sentences than Kimi's.
Kimi K3.1 Pro writes the stronger script by a wide margin. Kimi K3.1 Pro (max) leads GPT-6.1 Terra (max) by 268 Elo with 95% ranges 189 apart, the #8 model of 84 against the #23 model, and it wins all ten scripts. Kimi has one setting on the board. Terra has five, within 25 Elo of each other with overlapping ranges, so I would use low. Max does get Terra closer on length, 94.2 against 88.0 at low, but it costs 2.9 times as much and I would still stay at low. Kimi costs $0.251 a script and takes 5.5 minutes. Terra at low costs $0.027 and takes 0.5, about a ninth of the price. Against Terra at low, Kimi's biggest leads are visual cues, by 8.2 points, and length, by 7.4. Terra keeps the cleaner sentences, 3.0 points up on slop, and edges craft. For anything I film I'd run Kimi at max. Terra at low is the quick draft I'd rewrite anyway.
Disclosure: GPT-6.1 Terra comes from the same lab as one of the four judges, GPT-6.1 Sol. 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 K3.1 Pro and GPT-6.1 Terra, 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.
- Each bar describes one configuration. Overlap alone does not establish a tie or decide their order. Comparing these ranges does not directly test the difference between a pair.
- 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 K3.1 Pro (max) | 2191 | 2148 to 2231 | 82.5 | $0.251 | 5.5 min | 19,487 | #14 |
| GPT-6.1 Terra (max) | 1923 | 1884 to 1959 | 80.3 | $0.079 | 1.8 min | N/A | #43 |
| GPT-6.1 Terra (high) | 1922 | 1881 to 1958 | 80.3 | $0.027 | 0.5 min | N/A | #44 |
| GPT-6.1 Terra (low) | 1920 | 1879 to 1961 | 80.2 | $0.027 | 0.5 min | N/A | #46 |
| GPT-6.1 Terra (xhigh) | 1906 | 1869 to 1944 | 80.1 | $0.028 | 0.5 min | N/A | #48 |
| GPT-6.1 Terra (medium) | 1898 | 1852 to 1942 | 79.9 | $0.027 | 0.5 min | N/A | #49 |
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. The 95% ranges describe individual configurations; overlap alone establishes neither a tie nor an order for a pair.
- Best Configurations Head to Head. Kimi K3.1 Pro (max) leads GPT-6.1 Terra (max) by 268 Elo, and their 95% ranges do not overlap (2148 to 2231 against 1884 to 1959), which is strong evidence for that order.
- Every Kimi K3.1 Pro Configuration Ranks Higher. Kimi K3.1 Pro (max), the only Kimi K3.1 Pro configuration on the board, ranks above all five GPT-6.1 Terra configurations, including GPT-6.1 Terra (max) at Elo 1923.
- Same Level Name, Side by Side. At max, the one level name both models use, Kimi K3.1 Pro has the higher Writing Elo: 2191 against 1923. Their 95% ranges do not overlap there. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Lowest to Highest Thinking Level. GPT-6.1 Terra moves +3 Elo from low to max, at about 2.9 times the cost per script.
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 K3.1 Pro (max) scores higher on seven of the nine metrics and GPT-6.1 Terra (max) on two. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put Kimi K3.1 Pro (max) ahead, with a 3.0-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Kimi K3.1 Pro (max) | GPT-6.1 Terra (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.65 | 1.68 |
| Lowest script score | 80.4 Script 7 | 77.9 Script 10 |
| Highest script score | 85.5 Script 9 | 83.2 Script 9 |
| Range across scripts | 5.1 | 5.3 |
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 K3.1 Pro (max) minus GPT-6.1 Terra (max), and the higher score is in bold.
| Script | Kimi K3.1 Pro (max) | GPT-6.1 Terra (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.3 | 80.2 | +1.1 |
| Script 2 news-analysis / skeptical explainer | 83.2 | 80.7 | +2.5 |
| Script 3 personal roadmap / opinion | 81.9 | 80.4 | +1.5 |
| Script 4 short explainer | 82.0 | 79.6 | +2.4 |
| Script 5 news-analysis / opinion explainer | 84.2 | 80.1 | +4.1 |
| Script 6 founder announcement / personal origin story | 83.0 | 82.2 | +0.8 |
| Script 7 personal technical walkthrough / agentic workflow case study | 80.4 | 79.9 | +0.5 |
| Script 8 product release announcement / personal observation | 82.1 | 79.1 | +3.0 |
| Script 9 career guide / hiring analysis | 85.5 | 83.2 | +2.3 |
| Script 10 engineering process walkthrough / presentation adaptation | 81.3 | 77.9 | +3.4 |
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