Model Comparison
GLM-5.3 vs DeepSeek V4.1 Flash 1017
GLM-5.3 (max) leads DeepSeek V4.1 Flash 1017 (max) by 107 Elo, and their 95% ranges sit 21 Elo apart. Among 81 models, each ranked by its best configuration, GLM-5.3 is #9 and DeepSeek V4.1 Flash 1017 is #13. Cost per script: $0.240 for GLM-5.3 (max) and $0.014 for DeepSeek V4.1 Flash 1017 (max).
Last updated , from board data generated at 16:59 UTC.
Picks and Verdict
PickGLM-5.3
GLM-5.3 (max)
Pick GLM-5.3 (max) for the script that goes on camera, since its range sits clear of both DeepSeek configurations at $0.240 a script.
PickDeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 (max)
Pick DeepSeek V4.1 Flash 1017 (max) for drafting before the final pass, at $0.014 a script and 1.3 minutes.
GLM-5.3 is the better writer here, and you pay about 17 times as much for it. GLM-5.3 (max) leads DeepSeek V4.1 Flash 1017 (max) by 107 Elo, with 95% ranges 21 Elo apart, which is strong evidence for that order. That's the #9 model of 81 against the #13 model, each ranked by its best configuration. The lead comes from the video side of the script: 4.4 points on visual cues, 2.3 on hooks and 1.6 on YouTube Best Practices, and GLM wins eight of the ten scripts with the steadiest drafts on this page. DeepSeek keeps a slight edge on craft, length and slop, under a point each. The price is what keeps DeepSeek in the conversation: $0.240 and 6.1 minutes a script against $0.014 and 1.3 minutes. GLM-5.3 has one configuration on the board, so there's no thinking level to choose. DeepSeek's two sit 37 Elo apart inside overlapping ranges, but DeepSeek V4.1 Flash 1017 (high) falls 144 Elo behind GLM with separate ranges, so if I'm drafting on DeepSeek I keep it on max. GLM-5.3 for the version I record, DeepSeek at max for everything before it.
Disclosure: GLM-5.3 comes from the same lab as one of the four judges, GLM 5.3 Flash. 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 GLM-5.3 and DeepSeek V4.1 Flash 1017, 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 |
|---|---|---|---|---|---|---|---|
| GLM-5.3 (max) | 2194 | 2161 to 2230 | 82.4 | $0.240 | 6.1 min | 46,444 | #17 |
| DeepSeek V4.1 Flash 1017 (max) | 2087 | 2039 to 2140 | 81.6 | $0.014 | 1.3 min | 16,960 | #24 |
| DeepSeek V4.1 Flash 1017 (high) | 2050 | 2001 to 2092 | 81.1 | $0.0095 | 0.9 min | 9,728 | #27 |
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.
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. GLM-5.3 (max) leads DeepSeek V4.1 Flash 1017 (max) by 107 Elo, and their 95% ranges do not overlap (2161 to 2230 against 2039 to 2140), which is strong evidence for that order.
- Every GLM-5.3 Configuration Ranks Higher. GLM-5.3 (max), the only GLM-5.3 configuration on the board, ranks above both DeepSeek V4.1 Flash 1017 configurations, including DeepSeek V4.1 Flash 1017 (max) at Elo 2087.
- Same Level Name, Side by Side. At max, the one level name both models use, GLM-5.3 has the higher Writing Elo: 2194 against 2087. 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. DeepSeek V4.1 Flash 1017 moves +37 Elo from high to max, at about 1.5 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
GLM-5.3 (max) scores higher on six of the nine metrics and DeepSeek V4.1 Flash 1017 (max) on three. Weighted by each metric's share of the Writing Score, Hook Strength does the most to put GLM-5.3 (max) ahead, with a 2.3-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| GLM-5.3 (max) | DeepSeek V4.1 Flash 1017 (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.39 | 1.58 |
| Lowest script score | 80.5 Script 10 | 79.9 Script 4 |
| Highest script score | 84.1 Script 7 | 83.0 Script 7 |
| Range across scripts | 3.6 | 3.1 |
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.
Scores by Script
Writing Score on each reference script. Gap is GLM-5.3 (max) minus DeepSeek V4.1 Flash 1017 (max), and the higher score is in bold.
| Script | GLM-5.3 (max) | DeepSeek V4.1 Flash 1017 (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 82.1 | 80.5 | +1.6 |
| Script 2 news-analysis / skeptical explainer | 82.5 | 80.8 | +1.7 |
| Script 3 personal roadmap / opinion | 81.5 | 80.5 | +1.0 |
| Script 4 short explainer | 81.0 | 79.9 | +1.1 |
| Script 5 news-analysis / opinion explainer | 82.5 | 82.9 | -0.4 |
| Script 6 founder announcement / personal origin story | 82.9 | 81.2 | +1.7 |
| Script 7 personal technical walkthrough / agentic workflow case study | 84.1 | 83.0 | +1.1 |
| Script 8 product release announcement / personal observation | 82.7 | 82.6 | +0.1 |
| Script 9 career guide / hiring analysis | 84.0 | 83.0 | +1.0 |
| Script 10 engineering process walkthrough / presentation adaptation | 80.5 | 81.6 | -1.1 |
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