Model Comparison
GPT-6.1 Sol (max) leads Claude Haiku 5.5 (max effort) by 239 Elo, and their 95% ranges sit 158 Elo apart. Among 87 models, each ranked by its best configuration, GPT-6.1 Sol is #8 and Claude Haiku 5.5 is #20. Cost per script: $0.239 for GPT-6.1 Sol (max) and $0.103 for Claude Haiku 5.5 (max effort).
Last updated , from board data generated at 17:52 UTC.
PickGPT-6.1 Sol
GPT-6.1 Sol (low)
Pick GPT-6.1 Sol (low) as the default, since at $0.052 a script in 1.5 minutes it rates above Haiku's max effort, with separate ranges, at about half the price.
PickClaude Haiku 5.5
Claude Haiku 5.5 (xhigh)
Pick Claude Haiku 5.5 (xhigh) for bulk drafts at $0.029 a script, because it already holds most of what Haiku gains from thinking and finishes in 3.6 minutes.
Claude Haiku 5.5 at its most expensive setting doesn't reach GPT-6.1 Sol's cheapest one. Claude Haiku 5.5 (max effort) costs $0.103 a script and takes more than twelve minutes. GPT-6.1 Sol (low) costs $0.052, finishes in 1.5 minutes and rates 95 Elo higher. Their 95% ranges sit just apart, so the board puts low ahead, if only just, and I see no reason to pay double and wait eight times as long for a draft that rates lower. Best against best, Sol leads by 239 Elo, the #8 model of 87 against the #20 model, each ranked by its best setting. Sol's medium and high rate below low inside overlapping ranges, so I'd skip their extra cost, while max adds 144 Elo over low, with separate ranges, at about 4.6 times the price. Haiku climbs much harder: it gains 482 Elo from low to max effort, and most of that arrives by xhigh. Claude Haiku 5.5 (xhigh) costs $0.029, and max effort adds 68 Elo for about 3.6 times the price, with ranges that overlap. Haiku's writing craft comes within a few tenths of Sol's at the top settings, and it loses on the hook. For me it's Sol at low, and Haiku at xhigh when every cent counts.
Disclosure: GPT-6.1 Sol and Claude Haiku 5.5 each come from the same lab as one of the judges (GPT-6.1 Sol and Claude Opus 5.5). Neither is scored by its own lab alone (how the panel works). The judge analysis measures how much each judge favors its own lab.
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.
Every ranked configuration of GPT-6.1 Sol and Claude Haiku 5.5, scored on the same 10 scripts by the same four judges.
Shaded rows are the configurations chosen for the metric comparison below.
| Configuration | Writing Elo | 95% Range | Writing Score | Cost / Script | Time / Script | Configuration Rank |
|---|---|---|---|---|---|---|
| GPT-6.1 Sol (max) | 2153 | 2118 to 2191 | 82.4 | $0.239 | 10.2 min | #18 |
| GPT-6.1 Sol (xhigh) | 2136 | 2097 to 2179 | 82.4 | $0.199 | 7.8 min | #23 |
| GPT-6.1 Sol (low) | 2009 | 1976 to 2043 | 81.4 | $0.052 | 1.5 min | #31 |
| GPT-6.1 Sol (high) | 1975 | 1936 to 2013 | 81.1 | $0.094 | 3.3 min | #33 |
| GPT-6.1 Sol (medium) | 1946 | 1915 to 1983 | 81.0 | $0.054 | 1.6 min | #37 |
| Claude Haiku 5.5 (max effort) | 1914 | 1874 to 1960 | 80.8 | $0.103 | 12.6 min | #42 |
| Claude Haiku 5.5 (xhigh) | 1846 | 1804 to 1887 | 80.0 | $0.029 | 3.6 min | #56 |
| Claude Haiku 5.5 (high) | 1648 | 1603 to 1695 | 78.0 | $0.012 | 1.5 min | #71 |
| Claude Haiku 5.5 (medium) | 1551 | 1505 to 1593 | 76.7 | $0.0067 | 0.8 min | #84 |
| Claude Haiku 5.5 (low) | 1432 | 1383 to 1475 | 75.2 | $0.0045 | 0.5 min | #96 |
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.
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.
| Level | GPT-6.1 Sol | Claude Haiku 5.5 | Gap | 95% Ranges |
|---|---|---|---|---|
| low | 2009 | 1432 | +577 | Separate |
| medium | 1946 | 1551 | +395 | Separate |
| high | 1975 | 1648 | +327 | Separate |
| xhigh | 2136 | 1846 | +290 | Separate |
| max | 2153 | 1914 | +239 | Separate |
Gap is GPT-6.1 Sol minus Claude Haiku 5.5 at the same level name, using each model's highest-rated configuration at that level.
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.
GPT-6.1 Sol (max) scores higher on all nine metrics. Weighted by each metric's share of the Writing Score, Hook Strength does the most to put GPT-6.1 Sol (max) ahead, with a 4.6-point lead on that metric. The weight beside each metric is its share of the Writing Score.
| GPT-6.1 Sol (max) | Claude Haiku 5.5 (max effort) | |
|---|---|---|
| Score spread across drafts (±) | 1.40 | 1.55 |
| Lowest script score | 80.6 Script 10 | 78.2 Script 10 |
| Highest script score | 85.0 Script 9 | 82.6 Script 4 |
| Range across scripts | 4.4 | 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.
Writing Score on each reference script. Gap is GPT-6.1 Sol (max) minus Claude Haiku 5.5 (max effort), and the higher score is in bold.
| Script | GPT-6.1 Sol (max) | Claude Haiku 5.5 (max effort) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.7 | 80.3 | +1.4 |
| Script 2 news-analysis / skeptical explainer | 82.5 | 80.7 | +1.8 |
| Script 3 personal roadmap / opinion | 83.6 | 80.8 | +2.8 |
| Script 4 short explainer | 82.5 | 82.6 | -0.1 |
| Script 5 news-analysis / opinion explainer | 82.0 | 81.7 | +0.3 |
| Script 6 founder announcement / personal origin story | 83.3 | 81.1 | +2.2 |
| Script 7 personal technical walkthrough / agentic workflow case study | 82.2 | 80.0 | +2.2 |
| Script 8 product release announcement / personal observation | 81.0 | 81.3 | -0.3 |
| Script 9 career guide / hiring analysis | 85.0 | 81.5 | +3.5 |
| Script 10 engineering process walkthrough / presentation adaptation | 80.6 | 78.2 | +2.4 |
Each configuration name in the table above opens its own scorecard.
Pick a second model. A pair with its own written match-up opens that page, and any other pair opens in the comparison tool.
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