ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work.

Writing, best available

Find the active text model with the strongest evidence on long-form writing.

Worked example as of 2026-09-23, from the public data image.

Strongest writing evidence, cost no object.

Requirements

model.class = text-generator: Writing needs a model that generates text.
model.lifecycle = active: An active model is still supported by its lab or provider.

Preferences

writing: Rank only by the writing capability estimate.

Applied template spec

spec_version

where

model.class = text-generator
model.lifecycle = active

optimize

weights

writing: 1.0

Worked answer

Decision status: partial.

No recommendation: the public image has no answer with enough evidence.

This is a partial answer. Unknown facts or missing objective evidence can leave eligible candidates unranked.

probability bands: a model joins the leader when P(its score >= the leader's) >= 0.25 under the score posteriors; a weighted capability with an 80% interval wider than 2.8 is not enough evidence

Score and score interval use the objective's dimensionless normalised units. Cost per task is for the engine-selected offering and the applied spec's task size. When task size is omitted, the engine uses its documented default. P(best) is the engine probability. Unavailable means the engine did not return a value. Thin evidence is undetermined and is not a recommendation.

Thin evidence: undetermined

Model	Score	Score interval	P(best)	Cost per task, USD	Capability estimates and intervals
`anthropic/claude-fable-5`	1.0	[0.45093, 1.54907]	0.1171875	0.6	writing: 0.787525395; interval [-0.711613961, 2.286664752]; benchmarks 3; direct benchmarks 0
`anthropic/claude-opus-4-6`	0.964524	[0.415455, 1.513594]	0.109375	0.3	writing: 0.690665563; interval [-0.808473794, 2.189804919]; benchmarks 3; direct benchmarks 0
`anthropic/claude-fable-5-1`	0.886908	[0.337839, 1.435978]	0.07421875	0.6	writing: 0.478747567; interval [-1.02039179, 1.977886923]; benchmarks 3; direct benchmarks 0
`anthropic/claude-opus-4-7`	0.88162	[0.33255, 1.430689]	0.06640625	0.3	writing: 0.464308039; interval [-1.034831318, 1.963447396]; benchmarks 3; direct benchmarks 0
`google/gemini-3-7-flash`	0.870738	[0.321668, 1.419807]	0.0625	0.045	writing: 0.434597365; interval [-1.064541992, 1.933736721]; benchmarks 3; direct benchmarks 0
`google/gemini-3-8-flash`	0.837631	[0.288561, 1.3867]	0.078125	0.045	writing: 0.344204382; interval [-1.154934975, 1.843343738]; benchmarks 3; direct benchmarks 0
`openai/gpt-5-6-sol`	0.815156	[0.266087, 1.364226]	0.06640625	0.24	writing: 0.282841067; interval [-1.216298289, 1.781980424]; benchmarks 3; direct benchmarks 0
`google/gemini-3-1-pro-preview`	0.801432	[0.252363, 1.350502]	0.0390625	0.128	writing: 0.245370198; interval [-1.253769159, 1.744509554]; benchmarks 3; direct benchmarks 0
`openai/gpt-6-astra`	0.781091	[0.232022, 1.330161]	0.03125	0.6	writing: 0.189832533; interval [-1.309306823, 1.68897189]; benchmarks 3; direct benchmarks 0
`anthropic/claude-opus-5`	0.756294	[0.207225, 1.305364]	0.03515625	0.3	writing: 0.122128685; interval [-1.377010672, 1.621268041]; benchmarks 3; direct benchmarks 0
`google/gemini-3-5-flash`	0.717352	[0.168283, 1.266422]	0.0234375	0.096	writing: 0.015804984; interval [-1.483334372, 1.514944341]; benchmarks 3; direct benchmarks 0
`zhipu/glm-5-3`	0.71513	[0.166061, 1.2642]	0.04296875	0.0736	writing: 0.009738247; interval [-1.489401109, 1.508877604]; benchmarks 3; direct benchmarks 0
`meta/muse-spark-1-3`	0.704852	[-0.027958, 1.437662]	0.0703125	0.067	writing: -0.018325411; interval [-2.019136338, 1.982485515]; benchmarks 1; direct benchmarks 0
`moonshot/kimi-k3`	0.692287	[0.143217, 1.241356]	0.01953125	Unavailable	writing: -0.052632519; interval [-1.551771876, 1.446506837]; benchmarks 3; direct benchmarks 0
`meta/muse-spark-1-1`	0.647082	[-0.085728, 1.379893]	0.046875	0.067	writing: -0.176054846; interval [-2.176865772, 1.824756081]; benchmarks 1; direct benchmarks 0
`openai/gpt-5-4`	0.6221	[0.07303, 1.171169]	0.015625	0.16	writing: -0.244266234; interval [-1.743405591, 1.254873122]; benchmarks 3; direct benchmarks 0
`deepseek/deepseek-v3-1`	0.62044	[0.07137, 1.16951]	0.03125	Unavailable	writing: -0.2487973; interval [-1.747936656, 1.250342057]; benchmarks 3; direct benchmarks 0
`google/gemini-2-5-flash`	0.614462	[0.065392, 1.163531]	0.0234375	0.022	writing: -0.265119831; interval [-1.764259188, 1.234019525]; benchmarks 3; direct benchmarks 0
`zhipu/glm-5-2`	0.614399	[0.065329, 1.163468]	0.01953125	0.0736	writing: -0.265292672; interval [-1.764432028, 1.233846685]; benchmarks 3; direct benchmarks 0
`deepseek/deepseek-v4-pro`	0.562642	[0.013572, 1.111711]	0.015625	0.06864	writing: -0.406605901; interval [-1.905745257, 1.092533456]; benchmarks 3; direct benchmarks 0
`moonshot/kimi-k2-6`	0.500728	[-0.048341, 1.049798]	0.01171875	Unavailable	writing: -0.575649419; interval [-2.074788775, 0.923489938]; benchmarks 3; direct benchmarks 0
`microsoft/phi-4`	0.0	[-0.54907, 0.54907]	0.0	Unavailable	writing: -1.942801402; interval [-3.441940759, -0.443662046]; benchmarks 3; direct benchmarks 0

Unknown requirements

Some candidates may qualify. Missing facts:

writing

Engine warnings

not_separable
proxy_evidence_only

Omitted result rows: models 12; offerings 11. The bands above include all ranked models.

Decision dec_c1a427d4ad384dc464b5a8a3 on public snapshot snap_05a963d2477ac2fb.

What this template teaches

One Must selects the class, one Prefer states what best means.

The live board uses current data. Its answer can change as evidence changes.

Apply this template on Decide

Human lookup is free on Decide. CLI, API, and MCP access requires a key. Access and pricing.

Use-case examples · How we decide