Model Comparison
GPT-6.1 Sol vs DeepSeek V4 Pro 0813
GPT-6.1 Sol (max) leads DeepSeek V4 Pro 0813 (max) by 264 Elo, and their 95% ranges sit 195 Elo apart. Even GPT-6.1 Sol's lowest-rated configuration, GPT-6.1 Sol (medium), ranks above DeepSeek V4 Pro 0813 (max). Among 78 models, each ranked by its best configuration, GPT-6.1 Sol is #9 and DeepSeek V4 Pro 0813 is #21. Cost per script: $0.239 for GPT-6.1 Sol (max) and $0.077 for DeepSeek V4 Pro 0813 (max).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickGPT-6.1 Sol
GPT-6.1 Sol (low)
Pick GPT-6.1 Sol (low) for everyday scripts, since at $0.052 it costs less than DeepSeek's best and rates 149 Elo higher.
PickDeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 (max)
Pick DeepSeek V4 Pro 0813 (max) when the draft has to land on length without an edit, since its 93.4 on Length Adherence beats Sol's three cheapest settings for $0.077 a script.
GPT-6.1 Sol's cheapest setting already beats DeepSeek V4 Pro 0813's best. GPT-6.1 Sol (low) costs $0.052 a script, less than the $0.077 of DeepSeek V4 Pro 0813 (max), and it rates 149 Elo higher with 95% ranges that don't overlap. It also finishes in 1.5 minutes against 8.9. All five Sol settings rate above DeepSeek's best, and two of them cost less. Sol's medium and high cost more than low without rating any higher, so I'd skip both. The top two do pull away: GPT-6.1 Sol (max) sits 264 Elo over DeepSeek, for $0.239 and about ten minutes. That's the #9 model of 78 against the #21 model, each ranked by its best setting. The board can't separate max from xhigh at $0.199, so that's where I'd stop paying. DeepSeek earns its place on length. At max it scores 93.4 on Length Adherence, almost ten points above Sol at low, and you have to pay for Sol's xhigh setting to beat that. Keep DeepSeek at max, because its high setting sits 600 Elo lower. My default here is Sol at low, and I'd fix the length by hand.
Disclosure: GPT-6.1 Sol 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 GPT-6.1 Sol and DeepSeek V4 Pro 0813, 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 |
|---|---|---|---|---|---|---|---|
| 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 |
| DeepSeek V4 Pro 0813 (max) | 1950 | 1906 to 1989 | 80.1 | $0.077 | 8.9 min | 31,573 | #40 |
| DeepSeek V4 Pro 0813 (high) | 1350 | 1272 to 1428 | 72.3 | $0.031 | 1.3 min | 8,879 | #81 |
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. GPT-6.1 Sol (max) leads DeepSeek V4 Pro 0813 (max) by 264 Elo, and their 95% ranges do not overlap (2184 to 2248 against 1906 to 1989), which is strong evidence for that order.
- Every GPT-6.1 Sol Configuration Ranks Higher. All five GPT-6.1 Sol configurations rank above both DeepSeek V4 Pro 0813 configurations: the lowest-rated, GPT-6.1 Sol (medium) at Elo 2033, still beats DeepSeek V4 Pro 0813 (max) at Elo 1950. Their 95% ranges do not overlap.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, GPT-6.1 Sol (low) at Elo 2099 and $0.052 per script leads DeepSeek V4 Pro 0813 (high) at Elo 1350 and $0.031 per script by 749 Elo. Their 95% ranges do not overlap.
- Same Level Name, Side by Side. GPT-6.1 Sol 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 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 GPT-6.1 Sol (max), at $0.239 per script: 2161 to 2256 against 2184 to 2248, so the board cannot separate them. GPT-6.1 Sol (max) costs about 1.2 times as much per script.
- Cheapest GPT-6.1 Sol Configuration Above DeepSeek V4 Pro 0813's Best. The cheapest GPT-6.1 Sol configuration with a higher Writing Elo than DeepSeek V4 Pro 0813 (max), at Elo 1950 and $0.077 per script, is GPT-6.1 Sol (low), at Elo 2099 and $0.052 per script. It costs less than the configuration it beats.
- 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. DeepSeek V4 Pro 0813 moves +600 Elo from high to max, at about 2.5 times the cost per script.
Writing Elo at Each Shared Level Name
| Level | GPT-6.1 Sol | DeepSeek V4 Pro 0813 | Gap | 95% Ranges |
|---|---|---|---|---|
| high | 2055 | 1350 | +705 | Separate |
| max | 2214 | 1950 | +264 | Separate |
Gap is GPT-6.1 Sol minus DeepSeek V4 Pro 0813 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
GPT-6.1 Sol (max) scores higher on seven of the nine metrics and DeepSeek V4 Pro 0813 (max) on two. Weighted by each metric's share of the Writing Score, Substance, Accuracy & Value does the most to put GPT-6.1 Sol (max) ahead, with a 5.6-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| GPT-6.1 Sol (max) | DeepSeek V4 Pro 0813 (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.40 | 1.48 |
| Lowest script score | 80.6 Script 10 | 78.2 Script 10 |
| Highest script score | 85.0 Script 9 | 81.5 Script 6 |
| Range across scripts | 4.4 | 3.3 |
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 GPT-6.1 Sol (max) minus DeepSeek V4 Pro 0813 (max), and the higher score is in bold.
| Script | GPT-6.1 Sol (max) | DeepSeek V4 Pro 0813 (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.7 | 79.5 | +2.2 |
| Script 2 news-analysis / skeptical explainer | 82.5 | 80.6 | +1.9 |
| Script 3 personal roadmap / opinion | 83.6 | 80.8 | +2.8 |
| Script 4 short explainer | 82.5 | 78.5 | +4.0 |
| Script 5 news-analysis / opinion explainer | 82.0 | 80.9 | +1.1 |
| Script 6 founder announcement / personal origin story | 83.3 | 81.5 | +1.8 |
| Script 7 personal technical walkthrough / agentic workflow case study | 82.2 | 81.1 | +1.1 |
| Script 8 product release announcement / personal observation | 81.0 | 80.2 | +0.8 |
| Script 9 career guide / hiring analysis | 85.0 | 79.9 | +5.1 |
| Script 10 engineering process walkthrough / presentation adaptation | 80.6 | 78.2 | +2.4 |
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