Model Comparison
Claude Opus 5.5 vs GPT-6.1 Sol
Claude Opus 5.5 (max effort) leads GPT-6.1 Sol (max) by 574 Elo, and their 95% ranges sit 468 Elo apart. Even Claude Opus 5.5's lowest-rated configuration, Claude Opus 5.5 (low), ranks above GPT-6.1 Sol (max). Among 78 models, each ranked by its best configuration, Claude Opus 5.5 is #1 and GPT-6.1 Sol is #9. Cost per script: $2.58 for Claude Opus 5.5 (max effort) and $0.239 for GPT-6.1 Sol (max).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickClaude Opus 5.5
Claude Opus 5.5 (xhigh)
Pick Claude Opus 5.5 (xhigh) for the script you'll put on camera, since it adds 295 Elo over Opus at low for about four times the price, which I'd pay for a recording.
PickGPT-6.1 Sol
GPT-6.1 Sol (low)
Pick GPT-6.1 Sol (low) for bulk first drafts at $0.052 a script, since its max setting adds 115 Elo for about 4.6 times the price.
Line the two up level by level, low through max, and Claude Opus 5.5 wins all five with separate ranges. At the top that's the #1 model of 78 against the #9 model, with Claude Opus 5.5 (xhigh) 574 Elo ahead of GPT-6.1 Sol (max). The bottom of the Opus ladder tells me more. Claude Opus 5.5 (low) still sits 279 Elo above Sol's best, at $0.243 a script against $0.239, about the same price. Going up, I'd stop at xhigh. Max effort runs $2.58 and over a quarter of an hour per script, and the board can't separate it from xhigh, so that's money and waiting for nothing I can point to. Sol's ladder has the same kind of dead weight: GPT-6.1 Sol (high) and GPT-6.1 Sol (medium) both rank below GPT-6.1 Sol (low), cost more and overlap its range. Sol deserves credit at the cheap end and on facts. Its low setting costs about a fifth of the Opus low price, and at max its substance matches Opus at high. For bulk drafting, Sol is fine. For the scripts I put my name on, it's Opus at xhigh.
Disclosure: Claude Opus 5.5 and GPT-6.1 Sol each come from the same lab as one of the judges (Claude Opus 5.5 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 Claude Opus 5.5 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 | Configuration Rank |
|---|---|---|---|---|---|---|
| Claude Opus 5.5 (max effort) | 2788 | 2716 to 2845 | 85.9 | $2.58 | 17.5 min | #1 |
| Claude Opus 5.5 (xhigh) | 2788 | 2727 to 2851 | 85.8 | $1.00 | 6.7 min | #2 |
| Claude Opus 5.5 (high) | 2536 | 2486 to 2573 | 84.6 | $0.328 | 2.1 min | #5 |
| Claude Opus 5.5 (medium) | 2520 | 2469 to 2576 | 84.5 | $0.310 | 1.9 min | #6 |
| Claude Opus 5.5 (low) | 2493 | 2436 to 2536 | 84.3 | $0.243 | 1.5 min | #7 |
| GPT-6.1 Sol (max) | 2214 | 2184 to 2248 | 82.4 | $0.239 | 10.2 min | #17 |
| GPT-6.1 Sol (xhigh) | 2209 | 2161 to 2256 | 82.4 | $0.199 | 7.8 min | #19 |
| GPT-6.1 Sol (low) | 2099 | 2062 to 2133 | 81.4 | $0.052 | 1.5 min | #24 |
| GPT-6.1 Sol (high) | 2055 | 2018 to 2094 | 81.1 | $0.094 | 3.3 min | #26 |
| GPT-6.1 Sol (medium) | 2033 | 1995 to 2071 | 81.0 | $0.054 | 1.6 min | #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.
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. Claude Opus 5.5 (max effort) leads GPT-6.1 Sol (max) by 574 Elo, and their 95% ranges do not overlap (2716 to 2845 against 2184 to 2248), which is strong evidence for that order.
- Every Claude Opus 5.5 Configuration Ranks Higher. All five Claude Opus 5.5 configurations rank above all five GPT-6.1 Sol configurations: the lowest-rated, Claude Opus 5.5 (low) at Elo 2493, still beats GPT-6.1 Sol (max) at Elo 2214. Their 95% ranges do not overlap.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, Claude Opus 5.5 (low) at Elo 2493 and $0.243 per script leads GPT-6.1 Sol (low) at Elo 2099 and $0.052 per script by 394 Elo. Their 95% ranges do not overlap.
- Same Level Name, Side by Side. Claude Opus 5.5 has the higher Writing Elo at every level name both models use: low, medium, high, xhigh, 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. Claude Opus 5.5 (xhigh), at $1.00 per script, is the cheapest configuration whose 95% range overlaps that of Claude Opus 5.5 (max effort), at $2.58 per script: 2727 to 2851 against 2716 to 2845, so the board cannot separate them. Claude Opus 5.5 (max effort) costs about 2.6 times as much per script.
- Cheapest Claude Opus 5.5 Configuration Above GPT-6.1 Sol's Best. The cheapest Claude Opus 5.5 configuration with a higher Writing Elo than GPT-6.1 Sol (max), at Elo 2214 and $0.239 per script, is Claude Opus 5.5 (low), at Elo 2493 and $0.243 per script. The two cost about the same per script.
- Lowest to Highest Thinking Level. Claude Opus 5.5 moves +295 Elo from low to max effort, at about 11 times the cost per script. GPT-6.1 Sol moves +115 Elo from low to max, at about 4.6 times the cost per script.
Writing Elo at Each Shared Level Name
| Level | Claude Opus 5.5 | GPT-6.1 Sol | Gap | 95% Ranges |
|---|---|---|---|---|
| low | 2493 | 2099 | +394 | Separate |
| medium | 2520 | 2033 | +487 | Separate |
| high | 2536 | 2055 | +481 | Separate |
| xhigh | 2788 | 2209 | +579 | Separate |
| max | 2788 | 2214 | +574 | Separate |
Gap is Claude Opus 5.5 minus GPT-6.1 Sol 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
Claude Opus 5.5 (max effort) scores higher on all nine metrics. Weighted by each metric's share of the Writing Score, Continuity & Emotion does the most to put Claude Opus 5.5 (max effort) ahead, with a 6.5-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Claude Opus 5.5 (max effort) | GPT-6.1 Sol (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.44 | 1.40 |
| Lowest script score | 83.6 Script 10 | 80.6 Script 10 |
| Highest script score | 87.3 Script 7 | 85.0 Script 9 |
| Range across scripts | 3.7 | 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 Claude Opus 5.5 (max effort) minus GPT-6.1 Sol (max), and the higher score is in bold.
| Script | Claude Opus 5.5 (max effort) | GPT-6.1 Sol (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 84.6 | 81.7 | +2.9 |
| Script 2 news-analysis / skeptical explainer | 85.3 | 82.5 | +2.8 |
| Script 3 personal roadmap / opinion | 86.5 | 83.6 | +2.9 |
| Script 4 short explainer | 87.0 | 82.5 | +4.5 |
| Script 5 news-analysis / opinion explainer | 85.9 | 82.0 | +3.9 |
| Script 6 founder announcement / personal origin story | 86.3 | 83.3 | +3.0 |
| Script 7 personal technical walkthrough / agentic workflow case study | 87.3 | 82.2 | +5.1 |
| Script 8 product release announcement / personal observation | 85.5 | 81.0 | +4.5 |
| Script 9 career guide / hiring analysis | 87.3 | 85.0 | +2.3 |
| Script 10 engineering process walkthrough / presentation adaptation | 83.6 | 80.6 | +3.0 |
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