Model Comparison
Overlapping ranges: the best configurations, Claude Opus 4.8 (max effort) and MiMo-V2.6-Pro (thinking on), are 51 Elo apart, and their 95% ranges overlap. Among 84 models, each ranked by its best configuration, Claude Opus 4.8 is #18 and MiMo-V2.6-Pro is #24. Cost per script: $1.23 for Claude Opus 4.8 (max effort) and $0.017 for MiMo-V2.6-Pro (thinking on).
Last updated , from board data generated at 20:15 UTC.
PickClaude Opus 4.8
Claude Opus 4.8 (high)
Pick Claude Opus 4.8 (high) when you need a draft right away, since it comes back in 1.4 minutes where MiMo takes 6.2.
PickMiMo-V2.6-Pro
MiMo-V2.6-Pro (thinking on)
Pick MiMo-V2.6-Pro (thinking on) for the script itself, since Opus at max effort costs more than seventy times its $0.017 for an Elo lead I wouldn't pay that much for.
MiMo-V2.6-Pro (thinking on) lands between the two Claude Opus 4.8 settings, and that tells me most of what I need. Above it, Claude Opus 4.8 (max effort) has a Writing Elo of 1971 against 1920, which makes Opus the #18 model of 84 and MiMo the #24 model. Those 95% ranges overlap, which alone does not test their difference, and Opus costs $1.23 a script where MiMo costs $0.017. That's more than seventy times the price for a lead I wouldn't pay that much for. Below it, Claude Opus 4.8 (high) trails MiMo by 93 Elo, and the ranges miss each other by 5 Elo, so that order holds, if only just, and Opus at high still costs about eleven times as much. Opus has its arguments. At max effort it holds the length better, by close to four points, and it's a little ahead on substance. At high it's fast, under a minute and a half against six. MiMo still scores closer to my voice than either Opus setting. So I'd run MiMo, and keep Opus at high for the days I need a draft right away.
Disclosure: Claude Opus 4.8 comes from the same lab as one of the four judges, Claude Opus 5.5. 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.
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 Claude Opus 4.8 and MiMo-V2.6-Pro, 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 | Reasoning Tokens | Configuration Rank |
|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 (max effort) | 1971 | 1929 to 2014 | 80.7 | $1.23 | 9.8 min | N/A | #34 |
| MiMo-V2.6-Pro (thinking on) | 1920 | 1870 to 1965 | 80.2 | $0.017 | 6.2 min | 10,176 | #45 |
| Claude Opus 4.8 (high) | 1827 | 1785 to 1865 | 79.3 | $0.193 | 1.4 min | N/A | #54 |
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.
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.
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.
Claude Opus 4.8 (max effort) scores higher on six of the nine metrics and MiMo-V2.6-Pro (thinking on) on three. Weighted by each metric's share of the Writing Score, Length Adherence does the most to put Claude Opus 4.8 (max effort) ahead, with a 3.7-point lead on that metric. The weight beside each metric is its share of the Writing Score.
| Claude Opus 4.8 (max effort) | MiMo-V2.6-Pro (thinking on) | |
|---|---|---|
| Score spread across drafts (±) | 2.02 | 1.87 |
| Lowest script score | 77.5 Script 4 | 78.0 Script 4 |
| Highest script score | 83.1 Script 6 | 82.5 Script 9 |
| Range across scripts | 5.6 | 4.5 |
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 Claude Opus 4.8 (max effort) minus MiMo-V2.6-Pro (thinking on), and the higher score is in bold.
| Script | Claude Opus 4.8 (max effort) | MiMo-V2.6-Pro (thinking on) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 80.2 | 79.3 | +0.9 |
| Script 2 news-analysis / skeptical explainer | 80.6 | 79.9 | +0.7 |
| Script 3 personal roadmap / opinion | 79.3 | 79.7 | -0.4 |
| Script 4 short explainer | 77.5 | 78.0 | -0.5 |
| Script 5 news-analysis / opinion explainer | 80.3 | 81.5 | -1.2 |
| Script 6 founder announcement / personal origin story | 83.1 | 81.1 | +2.0 |
| Script 7 personal technical walkthrough / agentic workflow case study | 82.5 | 80.3 | +2.2 |
| Script 8 product release announcement / personal observation | 82.5 | 80.7 | +1.8 |
| Script 9 career guide / hiring analysis | 82.0 | 82.5 | -0.5 |
| Script 10 engineering process walkthrough / presentation adaptation | 78.9 | 79.4 | -0.5 |
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