Claude Sonnet 5 (max effort)
Anthropic · proprietary · writing benchmark
The short version
Claude Sonnet 5 (max effort) sits at #24 of 130 on ToneBench, in the middle of the pack, with a writing Elo of 2137 and an overall score of 86.1 out of 100. We measured it by having it write all 9 of our real YouTube scripts, five times each, then scoring every draft blind against our own finished versions. Here is how it shook out.
Within Anthropic it ranks 14th of 21. Claude Opus 5 (max effort) is the family's top writer here, about 512 Elo ahead, so this config trades some quality for whatever it saves you in cost or speed.
Among proprietary models, it comes in 22nd of 83. That ranking is against the stronger half of the board: closed models still set the pace on voice fidelity here.
Worth knowing before you rely on it: this model is swingy. Its overall score moves ± 8.5 points between runs of the same brief, versus a board median of ± 3.8. A great draft and a mediocre one can come from the identical prompt. The shaded bands on the metric bars below show where that volatility lives.
What it does best is Length Discipline: it ranks 11th on that dimension at 91.5, well above the board average. Its softer spot is Substance & Value (84.9, 47th), which is the thing to watch if that metric matters most for your use.
It was uneven across the 9 scripts. Its best run was the founder announcement / personal origin story (89.2) and its weakest was the news-analysis / opinion explainer (74.2), a spread of about 15 points. Worth knowing if your writing skews toward one of those formats.
On cost, it runs about $0.707/task. GPT-5.6 Terra (ultra) scores higher for less money, at $0.065/task, so on pure value this config is not the frontier.
If you're tuning reasoning effort, we also tested Claude Sonnet 5 at other settings. None of them beat this config; the closest is Claude Sonnet 5 (default) (Elo 1940), so the only question is how much quality you want to trade for cost or speed.
Skill profile
The shape is the story: the further a corner reaches, the stronger that dimension. Biggest edge over the board: Length Discipline (+24.3); smallest edge: Substance & Value (+6.2).
Per-metric scores
Nine writing dimensions, each scored 0–100 and blended by the editorial weight shown. Rank is against all 130 current-ranked models. The thick bar is this model; the thin lines above and below are the current field's best model (darker) and average (lighter) on the same scale. The small ± number is its run-to-run variation.
Per-article scores
The same 9 real scripts every current-ranked model writes, scored individually. Different formats stress different skills.
Consistency: run-to-run variability
Every cell on this page is the mean of 5 independent runs per script; the ± numbers are the run-to-run standard deviation. Overall, Claude Sonnet 5 (max effort) varies by ± 8.5 points between runs versus a board median of ± 3.8, so it is swingier than the typical model here, worth knowing if you need repeatable output.
Its most volatile dimension is Tone & Voice (± 3.4 vs a board median of ± 2.2): two runs of the same brief can land visibly different tone & voice scores.
| Metric | This model | Board median | Verdict |
|---|---|---|---|
| Tone & Voice ? | 86.3 ± 3.4 | ± 2.2 | swingier than most |
| Writing Craft ? | 85.9 ± 3.1 | ± 2.0 | swingier than most |
| Substance & Value ? | 84.9 ± 4.5 | ± 2.6 | swingier than most |
| Flow & Emotion ? | 83.6 ± 4.6 | ± 2.6 | swingier than most |
| YouTube Structure ? | 83.8 ± 4.4 | ± 3.6 | typical |
| Hook ? | 87.4 ± 2.3 | ± 3.0 | typical |
| Length Discipline ? | 91.5 ± 6.7 | ± 8.6 | typical |
| Anti-Slop ? | 90.8 ± 2.2 | ± 2.6 | typical |
| Visual Cues ? | 86.1 ± 4.7 | ± 4.7 | typical |
Measured, not modeled
Numbers we log on every run and rarely talk about. None of these affect the writing scores; cost and latency are informational.
What each judge scored it
The published overall of 86.1 is the consensus of three family-disjoint judges scoring the same 45 stored drafts blind with the identical rubric. The highest and lowest judge differ by 5.2 points on its overall. The three judges essentially agree on this model. How the panel works: methodology.
How we ran Claude Sonnet 5 (max effort)
- Accessed viaClaude Code (Anthropic subscription)
- Exact model / route id
claude-sonnet-5atreasoning_effort: max - Generations5 independent runs × 9 scripts = 45 drafts, stored immutably after generation
- Run dates2026-07-29 → 2026-08-11
- Judges3-judge panel: Claude Opus 5, high effort (Anthropic) + DeepSeek V4 Flash (OpenRouter) + GPT-5.6 Sol, medium reasoning (Codex CLI): every draft scored independently by all three with the identical rubric, blind to model identity, evidence quotes required before each metric score; published score = per-metric consensus mean, verified with a Bradley-Terry refit (methodology)
- Samplingprovider-default sampling, no fine-tuning, no system-prompt changes; every current-ranked model gets the identical brief, style contract and research packet
- What stays privatethe exact rubric and any non-public reference material; source-publication timing is disclosed for exceptions (why)
Frequently asked questions
How good is Claude Sonnet 5 (max effort) at writing?
On ToneBench it ranks #24 of 130 with a writing Elo of 2137 and an overall score of 86.1/100. That score comes from writing our 9 real YouTube scripts five times each and scoring every draft blind against our own finished versions across nine writing dimensions.
Is Claude Sonnet 5 (max effort) the best Anthropic model for writing?
Not quite. Within Anthropic it ranks 14th of 21; Claude Opus 5 (max effort) is the family's best writer here.
Is Claude Sonnet 5 (max effort) good value for the money?
It costs about $0.707/task. GPT-5.6 Terra (ultra) scores higher for less, so it is not the value pick.
What are Claude Sonnet 5 (max effort)'s strengths and weaknesses?
Its strongest dimension is Length Discipline (11th on the board, 91.5). Its weakest is Substance & Value (47th on the board, 84.9). The full nine-metric breakdown is on this page.
Does Claude Sonnet 5 (max effort) write some formats better than others?
Yes. Its best of our 9 scripts was the founder announcement / personal origin story (89.2) and its weakest was the news-analysis / opinion explainer (74.2).
How consistent is Claude Sonnet 5 (max effort) between runs?
We run every script 5 times. Claude Sonnet 5 (max effort)'s overall score varies by about ±8.5 points between runs, versus a board median of ±3.8. That is swingier than typical, so expect more draft-to-draft variation. The full per-metric variability table is on this page.
How was Claude Sonnet 5 (max effort) evaluated?
Via Claude Code (Anthropic subscription) using the exact model/route id claude-sonnet-5 at reasoning_effort max, run on 2026-07-29. 5 runs per script, provider-default sampling, no fine-tuning; every draft scored blind with a fixed rubric by a three-family judge panel. Full details in the 'How we ran it' section and the methodology.
Is Claude Sonnet 5 (max effort) open source?
No, it is a proprietary (closed-weights) model. Among proprietary models it ranks 22nd of 83 for writing.