Model Comparison
MiMo-V2.6-Flash vs GPT-5.6 Luna
MiMo-V2.6-Flash (thinking on) leads GPT-5.6 Luna (ultra) by 175 Elo, and their 95% ranges sit 71 Elo apart. Among 78 models, each ranked by its best configuration, MiMo-V2.6-Flash is #18 and GPT-5.6 Luna is #24. Cost per script: $0.0057 for MiMo-V2.6-Flash (thinking on) and $0.026 for GPT-5.6 Luna (ultra).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickMiMo-V2.6-Flash
MiMo-V2.6-Flash (thinking on)
Pick MiMo-V2.6-Flash (thinking on) as the default, 175 Elo ahead of Luna's best at $0.0057 a script.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) when substance and the right length come first, since it leads MiMo on both for $0.026 a script.
Half a cent a script, and MiMo-V2.6-Flash still comes out ahead. GPT-5.6 Luna (ultra) trails MiMo-V2.6-Flash (thinking on) by 175 Elo, and their 95% ranges don't overlap, which is strong evidence for that order. Those are each model's best setting, and they make MiMo-V2.6-Flash the #18 model of 78 and GPT-5.6 Luna the #24 model. Luna at ultra costs $0.026, about four and a half times MiMo's price, and takes about as long. The cheaper setting doesn't rescue it. GPT-5.6 Luna (medium) costs $0.0065, still a little more than MiMo, and sits 203 Elo below ultra. Most of what ultra buys back is length: Length Adherence goes from 70.9 at medium to 91.8. So with Luna you pay for ultra to get a script of the right size. Luna does keep two wins at ultra, about four points on substance and a little more on length. MiMo leads on the writing itself, more than five points up on tone, plus craft, continuity and YouTube structure. Tone carries the most weight in the Writing Score, so I'd run MiMo, and it's the one with open weights.
Disclosure: GPT-5.6 Luna 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 MiMo-V2.6-Flash and GPT-5.6 Luna, 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 |
|---|---|---|---|---|---|---|---|
| MiMo-V2.6-Flash (thinking on) | 1987 | 1929 to 2034 | 80.4 | $0.0057 | 3.5 min | 11,025 | #35 |
| GPT-5.6 Luna (ultra) | 1812 | 1768 to 1858 | 78.8 | $0.026 | 3.1 min | N/A | #49 |
| GPT-5.6 Luna (medium) | 1609 | 1572 to 1647 | 76.7 | $0.0065 | 0.5 min | N/A | #66 |
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. MiMo-V2.6-Flash (thinking on) leads GPT-5.6 Luna (ultra) by 175 Elo, and their 95% ranges do not overlap (1929 to 2034 against 1768 to 1858), which is strong evidence for that order.
- Every MiMo-V2.6-Flash Configuration Ranks Higher. MiMo-V2.6-Flash (thinking on), the only MiMo-V2.6-Flash configuration on the board, ranks above both GPT-5.6 Luna configurations, including GPT-5.6 Luna (ultra) at Elo 1812.
- Lowest to Highest Thinking Level. GPT-5.6 Luna moves +203 Elo from medium to ultra, at about 4 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
MiMo-V2.6-Flash (thinking on) scores higher on seven of the nine metrics and GPT-5.6 Luna (ultra) on two. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put MiMo-V2.6-Flash (thinking on) ahead, with a 5.4-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| MiMo-V2.6-Flash (thinking on) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 1.86 | 2.07 |
| Lowest script score | 78.9 Script 1 | 76.0 Script 7 |
| Highest script score | 81.9 Script 5 | 80.8 Script 9 |
| Range across scripts | 3.0 | 4.8 |
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 MiMo-V2.6-Flash (thinking on) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | MiMo-V2.6-Flash (thinking on) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 78.9 | 78.5 | +0.4 |
| Script 2 news-analysis / skeptical explainer | 80.3 | 80.3 | 0.0 |
| Script 3 personal roadmap / opinion | 79.4 | 79.7 | -0.3 |
| Script 4 short explainer | 79.4 | 77.4 | +2.0 |
| Script 5 news-analysis / opinion explainer | 81.9 | 79.7 | +2.2 |
| Script 6 founder announcement / personal origin story | 81.4 | 80.6 | +0.8 |
| Script 7 personal technical walkthrough / agentic workflow case study | 79.9 | 76.0 | +3.9 |
| Script 8 product release announcement / personal observation | 81.4 | 78.4 | +3.0 |
| Script 9 career guide / hiring analysis | 81.9 | 80.8 | +1.1 |
| Script 10 engineering process walkthrough / presentation adaptation | 79.7 | 76.9 | +2.8 |
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