Model Comparison
GLM-5.3 vs GPT-6.1 Sol
Too close to call: the best configurations, GLM-5.3 (max) and GPT-6.1 Sol (max), are 6 Elo apart, and their 95% ranges overlap. Among 78 models, each ranked by its best configuration, GLM-5.3 is #7 and GPT-6.1 Sol is #9. Cost per script: $0.240 for GLM-5.3 (max) and $0.239 for GPT-6.1 Sol (max).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickGLM-5.3
GLM-5.3 (max)
Pick GLM-5.3 (max) for scripts where voice and flow come first, at $0.240 and about six minutes a script.
PickGPT-6.1 Sol
GPT-6.1 Sol (xhigh)
Pick GPT-6.1 Sol (xhigh) for research-heavy scripts, since the board can't separate it from GLM-5.3 and it costs $0.199 a script.
Honestly, the board can't pick between these two at the top. GLM-5.3 is the #7 model of 78 and GPT-6.1 Sol the #9 model, each ranked by its best setting, and GLM-5.3 (max) and GPT-6.1 Sol (max) sit 6 Elo apart with overlapping 95% ranges. Sol's max setting costs the same, $0.239 against $0.240, though it takes about four minutes longer. GPT-6.1 Sol (xhigh) overlaps GLM too, at $0.199 a script. They get there differently. GLM leads five metrics, clearest on YouTube Best Practices, continuity and tone. Sol leads the other four, by over four points each on substance and the slop score. Lower down, Sol's ladder is odd. GPT-6.1 Sol (low) at $0.052 sits above both high and medium, so high adds cost and nothing the board can show. Low still trails GLM by 121 Elo with separate ranges, so the cheapest setting doesn't close the gap. For my scripts, a weak voice is harder to fix than a thin argument, so I'd start with GLM-5.3 and switch to Sol at xhigh when the topic needs more depth or the budget is tighter.
Disclosure: GLM-5.3 and GPT-6.1 Sol each come from the same lab as one of the judges (GLM 5.3 Flash and GPT-6.1 Sol). Neither is 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 GPT-6.1 Sol, 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) | 2220 | 2183 to 2259 | 82.4 | $0.240 | 6.1 min | 46,444 | #15 |
| GPT-6.1 Sol (max) | 2214 | 2184 to 2248 | 82.4 | $0.239 | 10.2 min | N/A | #17 |
| GPT-6.1 Sol (xhigh) | 2209 | 2161 to 2256 | 82.4 | $0.199 | 7.8 min | N/A | #19 |
| GPT-6.1 Sol (low) | 2099 | 2062 to 2133 | 81.4 | $0.052 | 1.5 min | N/A | #24 |
| GPT-6.1 Sol (high) | 2055 | 2018 to 2094 | 81.1 | $0.094 | 3.3 min | N/A | #26 |
| GPT-6.1 Sol (medium) | 2033 | 1995 to 2071 | 81.0 | $0.054 | 1.6 min | N/A | #29 |
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. GLM-5.3 (max) at Elo 2220 (range 2183 to 2259) and GPT-6.1 Sol (max) at Elo 2214 (range 2184 to 2248) have overlapping 95% ranges, so the board cannot separate the two best configurations.
- Same Level Name, Side by Side. At max, the one level name both models use, GLM-5.3 has the higher Writing Elo: 2220 against 2214. Their 95% ranges overlap there. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Cheapest Configuration Overlapping the Top One. GPT-6.1 Sol (xhigh), at $0.199 per script, is the cheapest configuration whose 95% range overlaps that of GLM-5.3 (max), at $0.240 per script: 2161 to 2256 against 2183 to 2259, so the board cannot separate them. GLM-5.3 (max) costs about 1.2 times as much per script.
- Lowest to Highest Thinking Level. GPT-6.1 Sol moves +115 Elo from low to max, at about 4.6 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 five of the nine metrics and GPT-6.1 Sol (max) on four. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| GLM-5.3 (max) | GPT-6.1 Sol (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.39 | 1.40 |
| Lowest script score | 80.5 Script 10 | 80.6 Script 10 |
| Highest script score | 84.1 Script 7 | 85.0 Script 9 |
| Range across scripts | 3.6 | 4.4 |
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 GPT-6.1 Sol (max), and the higher score is in bold.
| Script | GLM-5.3 (max) | GPT-6.1 Sol (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 82.1 | 81.7 | +0.4 |
| Script 2 news-analysis / skeptical explainer | 82.5 | 82.5 | 0.0 |
| Script 3 personal roadmap / opinion | 81.5 | 83.6 | -2.1 |
| Script 4 short explainer | 81.0 | 82.5 | -1.5 |
| Script 5 news-analysis / opinion explainer | 82.5 | 82.0 | +0.5 |
| Script 6 founder announcement / personal origin story | 82.9 | 83.3 | -0.4 |
| Script 7 personal technical walkthrough / agentic workflow case study | 84.1 | 82.2 | +1.9 |
| Script 8 product release announcement / personal observation | 82.7 | 81.0 | +1.7 |
| Script 9 career guide / hiring analysis | 84.0 | 85.0 | -1.0 |
| Script 10 engineering process walkthrough / presentation adaptation | 80.5 | 80.6 | -0.1 |
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