Model Scorecard

Claude Opus 4.7 (xhigh)

Anthropic · proprietary

Claude Opus 4.7 ranks #32 of 87 models on the November 2026 ToneBench board, and Claude Opus 4.7 (xhigh) is its only configuration, #69 of 151 configurations, with a Writing Score of 78.3/100 and a Writing Elo of 1682. One script costs $0.381 at API list price.

Last updated November 10, 2026, from board data generated at 17:52 UTC.

Rank, scores, the nine metrics, the 10 reference scripts, cost and setup for one configuration (a model at one reasoning setting). Key Results sums it up; the section links below it jump to the detail.

Key Results

• StandingClaude Opus 4.7 ranks #32 of 87 models, and this is its only configuration on the board. As a configuration, it is #69 of 151 configurations by Writing Elo (1682), in the middle third of the board. Its 95% range (1638 to 1723) overlaps 13 other configurations, ranked #64 to #78.
• MetricsBest-ranked: Length Adherence (90.6, 48th of 151 configurations, +5.9 against the board median). Lowest-ranked: Substance, Accuracy & Value (79.2, 96th of 151 configurations, -2.7 against the board median).
• ScriptsFrom 75.6 on Script 4 (short explainer) to 80.3 on Script 6 (founder announcement): a 4.7-point spread across the 10 reference scripts.
• ConsistencyIts Writing Score moves ± 1.9 between drafts of the same script, against ± 2.5 for the median configuration: typical.
• ValueMiMo-V2.6-Flash (thinking on) ranks higher and costs about $0.0057 per script, against $0.381 per script for this one.

Louis's PickI'd pick Claude Opus 5.5 (high) over this one: it ranks clearly higher for no more per script.

More Context Behind These Results

Writing Elo comes from comparing its average on each script with every other configuration's average on that same script; a gap smaller than the draft-to-draft variation counts as a draw (what the ranges can and cannot show).

Substance, Accuracy & Value ranks in the bottom half (96th of 151 configurations), so check the facts and the depth before anything goes out.

The script format moves its score. If most of your scripts look like its best or weakest format, that result is a better guide than the average.

Among proprietary models, Claude Opus 4.7 is 25th of 53. As a configuration, it is 58th of 108 proprietary configurations. The best open-weight configuration, GLM-5.3 (max) at configuration #22, outranks it.

Compare With Another ModelChoose a modelClaude Opus 5.5Claude Fable 5.2Claude Sonnet 5.5Claude Fable 5.1GPT-6 SolClaude Opus 5Claude Fable 5GPT-6.1 SolKimi K3.1 ProGLM-5.3GPT-5.6 SolKimi K3GPT-6 AstraGLM-5.3 FlashDeepSeek V4.1 Flash 1017GPT-5.6 TerraDeepSeek V4.1 FlashMuse WonderClaude Opus 4.8Claude Haiku 5.5MiMo-V2.6-Pro UltraSpeedMiMo-V2.6-FlashGPT-6.1 TerraGrok 4.6MiMo-V2.6-ProDeepSeek V4 Pro 0813Gemini 4 CarbonGrok 4.7Claude Sonnet 5GPT-5.6 LunaInkling 2 SmallGPT-6 LunaMiniMax M3.1 FlashGrok 4.5DeepSeek V4 Flash 0731Mistral Large 4Claude Opus 4.6Gemini 4 ArgonQwen3.8 MaxGPT-5.5GLM-5GLM-5.2Claude Sonnet 4.6Muse Spark 1.3Qwen3.8 FlashMiniMax M3GLM-4.7GLM-4.6Kimi K2.6DeepSeek V4 ProQwen3.7 MaxGemini 2.5 ProGPT-5.2Gemini 3.1 ProGemini 3.8 FlashGemini 3.7 FlashLlama 4 MaverickGrok 4.20Gemini 3.5 FlashGemini 3.6 FlashInklingNemotron 3 Ultra 550BGemini 2.5 FlashGrok 4.3Claude Haiku 4.5MiniMax M2.1MiniMax M2Gemini 3.5 Flash-LiteQwen3 235B ThinkingQwen3 235B A22BNemotron 3 Super 120BMistral Medium 3.5Mistral Large 3gpt-oss 120BGemini 2.5 Flash-LiteGLM-4.5 AirCohere Command A+ (05-2026)Cohere Command A ReasoningQwen3 Next 80BQwen3.5 9BCohere Command A (03-2025)Qwen3 8BGPT-4oGPT-4o miniLlama 4 ScoutGemma 3 4BCompare

Head-to-Head Pagescompare Claude Opus 4.7 with any model

Skill Profile Across the Nine Metrics

Each corner is one metric on a 0 to 100 scale; the further out, the higher the score. A corner outside the dashed line beats the board median. Hover or tap a point for its exact score, and a metric name for what it rewards.

Scores by Metric

Nine metrics, each scored 0 to 100 and weighted into the Writing Score; the weight sits under each name. Rank is out of all 151 ranked configurations.

Scores by Reference Script

Every ranked configuration writes five drafts for each of the same 10 briefs, and each score is the mean of those drafts. The rank and board median compare it with every configuration on that script, which separates a weak result from a hard script. The result on the format closest to your own work is the most relevant.

Consistency Between Drafts

Every score on this page is the mean of 5 drafts per script. The ± is the standard deviation between those drafts: the larger it is, the more two drafts of the same script can differ.

Consistency by Metric

Metric	This model	Board median	Verdict
Tone & Voice Match ?	75.9 ± 1.6	± 1.9	typical
Writing Craft & Clarity ?	75.7 ± 1.8	± 1.5	typical
Substance, Accuracy & Value ?	79.2 ± 3.0	± 2.1	typical
Continuity & Emotion ?	78.0 ± 1.5	± 1.5	typical
YouTube Best Practices ?	75.3 ± 3.1	± 2.4	typical
Hook Strength ?	79.2 ± 3.5	± 2.7	typical
Length Adherence ?	90.6 ± 4.3	± 6.6	typical
Slop Score ?	81.3 ± 1.8	± 1.6	typical
Visual Cue Quality ?	73.6 ± 2.6	± 2.9	typical

Cost, Time and Tokens per Script

Logged on every run; none of these figures affects the Writing Score. Time is the average time to one accepted script, retries included. Cost is one script at the API list price.

Scores by Judge

Four judges score the same 50 stored drafts blind against the same rubric: three LLM judges from three labs, plus Jev, a typed judge from TypeSafe that rates each metric on five described quality levels. No single judge's taste decides the result. The Writing Score of 78.3 combines their scores with the parts computed in code (Length Adherence and half of the Slop Score). The highest and lowest judge are 13.7 points apart on its Writing Score. That is close to the board median of 13.4. Each judge also has its own scale, so every card shows that judge's score against its average across the board. How the panel works.

Evaluation Setup

How this exact configuration was run and judged: route, model ID, dates, sampling and prompt.

• Accessed viaClaude Code (Anthropic subscription).
• Exact model / route idclaude-opus-4-7 (the request sets no level; the provider applies xhigh).
• Generations5 independent runs × 10 scripts = 50 drafts, stored after generation and never edited.
• Run dates2026-10-08.
• JudgesClaude 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 from TypeSafe. One call per judge per draft. All four score every draft on their own, blind to which model wrote it. The three LLM judges use the identical rubric and have to quote evidence before they score a metric. Jev answers the same rubric as one question per metric, choosing among five described quality levels, and writes no text. Seven metrics are the plain average of the four judges. Length is computed from the spoken word count, and Slop is half computed (lexical scans minus the spoken-dash penalty) and half judged. The Writing Elo is cross-checked with a Bradley-Terry fit of the same pairwise results (methodology).
• Sampling and promptThe provider's default sampling, with no fine-tuning and no system-prompt changes. Every current-ranked model gets the same prompt, about 13,000 tokens (the count shifts a bit with each model's tokenizer): a style guide built from Louis's voice and storytelling guides, the target length, and the brief with its research packet. Generation is closed-book on every route: the prompt is the only source, with no web search, browsing, code execution, file access or other tool (generation).
• What stays privateThe exact rubric and any non-public reference material. Each script is normally benchmarked before its video is published, which lowers the odds that a model has seen the reference, though it does not rule it out (why).

Frequently Asked Questions

← All models   ← Leaderboard