Best Model Now
Current AI rankings

Best AI for Writing

Coding / Writing / Images / Video

Compare AI for business writing, fiction prose, and screenwriting, with test results, practical tradeoffs, and supporting evidence.

Stay current

Know when the recommendations change.

Meaningful AI updates, plus On the Horizon: new releases we’re watching. About once a week. Only when there’s something worth sharing.

Scored rankings combine task quality and practical factors; small score gaps are close calls. Image and video use editorial first, second and third places, with reasons, tradeoffs and confidence rather than invented numerical scores. How we compare →

The one to beat

Best Writing Overall

The strongest practical writing model across quality, control, versatility, access, and reliability.

Writing qualityInstruction controlRevision strengthLong-form coherenceAccess & reliability
1

Claude Fable 5.1

Anthropic

The strongest current balance of nuanced writing, instruction control, revision judgment, and sustained long-form quality.

API$10 in $50 out per 1M tokens
MultipleWeighted score: 91.5
Best for
High-stakes long-form writing, voice-sensitive drafts, and demanding revision
Price & access
Claude subscription and API; premium API cost
Watch out for
Cost and throughput matter more than the last increment of prose quality
Restrictions
Moderate
Evidence
Leads the current Arena writing preference view and ties Astra atop Artificial Analysis intelligence, while outperforming Astra on AA-Briefcase and GDPval-AA v2.
Sources and observations (2)
  • Artificial AnalysisSource page · Observed Sep 12, 2026

    Claude Fable 5.1 (max with fallback) ties GPT-6 Astra for first in Intelligence Index v4.3 at 53 and leads Astra on AA-Briefcase and GDPval-AA v2.

  • LMArena leaderboardSource page · Observed Sep 12, 2026

    Claude Fable 5.1 (Max) currently leads Arena's writing/preference view at 13.85% ±1.92%.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Sep 12, 2026Official product / access information ↗
2

GPT-6 Astra

OpenAI

Nearly matches the writing leader while offering stronger cost efficiency, factual discipline, and concise execution.

API$10 in $50 out per 1M tokens
MultipleWeighted score: 90.0
When to choose GPT-6 Astra
Best for
Versatile professional writing, structured revision, and quality-conscious users who also value efficiency
Price & access
ChatGPT Work and API; access remains plan-dependent
Watch out for
You want the most consistently distinctive narrative voice
Restrictions
Moderate
Evidence
Places second in Arena's current writing preference view, ties Fable 5.1 on the Artificial Analysis Intelligence Index, and costs substantially less per evaluated task.
Sources and observations (2)
  • Artificial AnalysisSource page · Observed Sep 12, 2026

    GPT-6 Astra (max) ties Claude Fable 5.1 at 53 while costing about 40% as much per Intelligence Index task.

  • LMArena leaderboardSource page · Observed Sep 12, 2026

    GPT-6 Astra (Max) currently places second at 12.39% ±2.60%; its interval overlaps the leader's.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Sep 12, 2026Official product / access information ↗
3

Claude Opus 5

Anthropic

Exceptional prose and editorial judgment earn third, but premium cost and weaker value keep it behind Astra.

API$5 in $25 out per 1M tokens
MultipleWeighted score: 85.8
When to choose Claude Opus 5
Best for
Careful prose, high-stakes editing, and polished long-form work
Price & access
Claude subscription and API; premium pricing
Watch out for
You need economical high-volume drafting
Restrictions
Moderate
Evidence
Current Arena preference places Opus 5 directly behind Fable 5.1 and Astra; independent frontier evidence supports quality, though the value profile is weaker.
Sources and observations (1)
  • LMArena leaderboardSource page · Observed Sep 12, 2026

    Claude Opus 5 (High) currently places third at 11.06% ±1.70%.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Sep 12, 2026Official product / access information ↗
Also excellent

Gemini 3.8 Flash

Google

A close alternative to third place (0.1 weighted points apart). This gap does not establish a meaningful quality difference.

API$0.75 in $3.75 out per 1M tokens
Weighted score: 85.7

Clear, persuasive professional writing that needs less cleanup before it can be used.

Clarity & structurePersuasionTone controlFactual disciplineRewriting
1

Claude Fable 5.1

Anthropic

The strongest current model for nuanced, persuasive, high-stakes business documents, with a clear lead on demanding knowledge-work evaluations.

API$10 in $50 out per 1M tokens
MultipleWeighted score: 91.0
Best for
Strategy memos, proposals, executive briefs, and sensitive persuasive writing
Price & access
Claude subscription and API; premium API cost
Watch out for
High-volume routine copy makes cost the dominant concern
Restrictions
Moderate
Evidence
Leads Astra on AA-Briefcase and GDPval-AA v2, while current preference and practical comparison evidence support superior tone and document judgment.
Sources and observations (1)
  • Artificial AnalysisSource page · Observed Sep 12, 2026

    Claude Fable 5.1 leads GPT-6 Astra on AA-Briefcase (1662 vs 1562) and GDPval-AA v2 (1764 vs 1580), directly supporting demanding knowledge-work quality.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Sep 12, 2026Official product / access information ↗
2

GPT-5.6 Sol

OpenAI

The strongest practical value choice: polished presentation, dependable revision, mature access, and lower cost produce a razor-thin second-place finish.

API$4 in $20 out per 1M tokens
MultipleWeighted score: 90.0
When to choose GPT-5.6 Sol
Best for
Everyday business documents, presentations, synthesis, and high-volume professional drafting
Price & access
ChatGPT and API; lower token pricing than Astra
Watch out for
You need the highest ceiling for unusually sensitive or persuasive documents
Restrictions
Moderate
Evidence
Artificial Analysis identifies GPT-5.6 Sol as the current presentation-quality leader in AA-Briefcase; broad access and strong economics reinforce its practical business-writing score.
Sources and observations (1)
  • Artificial AnalysisSource page · Observed Sep 12, 2026

    GPT-5.6 Sol remains the presentation-quality leader in AA-Briefcase and retains strong professional-work performance at lower token prices than Astra.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Sep 12, 2026Official product / access information ↗
3

GPT-6 Astra

OpenAI

Excellent structure, factual discipline, professional-document handling, and stronger efficiency than Fable 5.1, narrowly edged by Sol after all practical factors are weighted.

API$10 in $50 out per 1M tokens
MultipleWeighted score: 89.8
When to choose GPT-6 Astra
Best for
Structured professional writing, document revision, and business work requiring strong reasoning with controlled cost
Price & access
ChatGPT Work and API; access remains plan-dependent
Watch out for
You prioritize mature broad access or the finest persuasive voice
Restrictions
Moderate
Evidence
Strong AA-Briefcase performance, leadership in AutomationBench-AA, a 31% all-criteria pass rate on GDP.pdf, and substantially lower evaluated-task cost than Fable 5.1.
Sources and observations (1)
  • Artificial AnalysisSource page · Observed Sep 12, 2026

    GPT-6 Astra trails Fable 5.1 on AA-Briefcase and GDPval-AA v2 but leads AutomationBench-AA, passes every GDP.pdf criterion on 31% of attempts, and offers materially lower cost per task.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Sep 12, 2026Official product / access information ↗

Compelling prose with sustained voice, character, narrative control, and originality.

Prose qualityCharacter voiceNarrative controlOriginalityRewriting
1

Claude Fable 5.1

Anthropic

Placed #1 in BMN's AI-panel-judged, owner-approved two-round blind challenge of 4 models. Both fresh prompts counted equally; results may vary by genre and premise.

API$10 in $50 out per 1M tokens
MultipleWeighted score: 100.0Provisional: evidence still developing
Best for
Original short fiction
Price & access
Claude subscription and premium API tier (Anthropic OpenRouter).
Watch out for
You need evidence of performance across a full novel or feature screenplay.
Restrictions
Moderate
Evidence
BMN test 77: 8 of 8 ordinal points across two original prompts, reviewed by the owner. Equal totals were resolved by the smallest average absolute percentage deviation from both prompt word targets.
Sources and observations (1)
  • Best Model Now — Fiction Prose Blind TestBMN test · Observed Oct 1, 2026

    BMN test 77: Fable 5.1 placed #1 in both blind original-fiction rounds for 8/8 ordinal points. Five fixed AI judges ranked anonymous drafts; the owner reviewed and approved the final order.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Oct 1, 2026Official product / access information ↗
2

Claude Opus 5

Anthropic

Placed #2 in BMN's AI-panel-judged, owner-approved two-round blind challenge of 4 models. Both fresh prompts counted equally; results may vary by genre and premise.

API$5 in $25 out per 1M tokens
MultipleWeighted score: 75.0Provisional: evidence still developing
When to choose Claude Opus 5
Best for
Original short fiction
Price & access
Anthropic via OpenRouter; premium API subscription recommended for production use.
Watch out for
You need evidence of performance across a full novel or feature screenplay.
Restrictions
Moderate
Evidence
BMN test 77: 6 of 8 ordinal points across two original prompts, reviewed by the owner. Equal totals were resolved by the smallest average absolute percentage deviation from both prompt word targets.
Sources and observations (1)

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Oct 1, 2026Official product / access information ↗
3

Claude Opus 5.5

Anthropic

Placed #3 in BMN's AI-panel-judged, owner-approved two-round blind challenge of 4 models. Both fresh prompts counted equally; results may vary by genre and premise.

API$4 in $20 out per 1M tokens
MultipleWeighted score: 37.5Provisional: evidence still developing
When to choose Claude Opus 5.5
Best for
Original short fiction
Price & access
Check Anthropic for current API and subscription access.
Watch out for
You need evidence of performance across a full novel or feature screenplay.
Restrictions
Pending
Evidence
BMN test 77: 3 of 8 ordinal points across two original prompts, reviewed by the owner. Equal totals were resolved by the smallest average absolute percentage deviation from both prompt word targets.
Sources and observations (1)
  • Best Model Now — Fiction Prose Blind TestBMN test · Observed Oct 1, 2026

    BMN test 77: Opus 5.5 placed #4 in round one and #3 in round two, totaling 3/8 points. It won the combined tie against Astra by smaller average percentage deviation from the two word targets and was published #3 after owner approval.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Oct 1, 2026Official product / access information ↗

Professional dramatic writing with strong scenes, distinct voices, subtext, and clean formatting.

Dialogue & subtextScene constructionPacingCharacter voiceFormatting & revision
1

GPT-6 Sol

OpenAI

Placed #1 in BMN's AI-panel-judged, owner-approved two-round blind challenge of 4 models. Both fresh prompts counted equally; results may vary by genre and premise.

API$2 in $10 out per 1M tokens
MultipleWeighted score: 75.0Provisional: evidence still developing
Best for
Original screenplay scenes
Price & access
Check OpenAI for current API and subscription access.
Watch out for
You need evidence of performance across a full novel or feature screenplay.
Restrictions
Pending
Evidence
BMN test 84: 6 of 8 ordinal points across two original prompts, reviewed by the owner. Equal totals were resolved by the smallest average absolute percentage deviation from both prompt word targets.
Sources and observations (1)
  • Best Model Now — Screenwriting Blind TestBMN test · Observed Sep 30, 2026

    BMN owner-reviewed two-round blind Screenwriting challenge: GPT-6 Sol earned 5/10 ordinal points; round placements 3 and 4. Equal totals were resolved by the owner-approved word-count tiebreak; result already published through the owner review workflow.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Oct 2, 2026Official product / access information ↗
2

GPT-6.1 Sol

OpenAI

Placed #2 in BMN's AI-panel-judged, owner-approved two-round blind challenge of 4 models. Both fresh prompts counted equally; results may vary by genre and premise.

MultipleWeighted score: 75.0Provisional: evidence still developing

Supporting source links for this published explanation are still being reconciled.

When to choose GPT-6.1 Sol
Best for
Original screenplay scenes
Price & access
Check OpenAI for current API and subscription access.
Watch out for
You need evidence of performance across a full novel or feature screenplay.
Restrictions
Pending
Evidence
BMN test 84: 6 of 8 ordinal points across two original prompts, reviewed by the owner. Equal totals were resolved by the smallest average absolute percentage deviation from both prompt word targets.
Ranking last verified: Oct 2, 2026Official product / access information ↗
3

GPT-6 Astra

OpenAI

Placed #3 in BMN's AI-panel-judged, owner-approved two-round blind challenge of 4 models. Both fresh prompts counted equally; results may vary by genre and premise.

API$10 in $50 out per 1M tokens
MultipleWeighted score: 75.0Provisional: evidence still developing
When to choose GPT-6 Astra
Best for
Original screenplay scenes
Price & access
OpenAI subscription / premium API tier.
Watch out for
You need evidence of performance across a full novel or feature screenplay.
Restrictions
Moderate
Evidence
BMN test 84: 6 of 8 ordinal points across two original prompts, reviewed by the owner. Equal totals were resolved by the smallest average absolute percentage deviation from both prompt word targets.
Sources and observations (1)
  • Best Model Now — Screenwriting Blind TestBMN test · Observed Sep 30, 2026

    BMN owner-reviewed two-round blind Screenwriting challenge: GPT-6 Astra earned 7/10 ordinal points; round placements 4 and 1. Equal totals were resolved by the owner-approved word-count tiebreak; result already published through the owner review workflow.

Observation dates record our evidence review, not necessarily the source’s publication date. A source page is identified when the record has no individual article link.

Ranking last verified: Oct 2, 2026Official product / access information ↗
The cost of a token

API pricing

Leading text & coding models. US dollars per million tokens.

Prices checked Sep 26, 2026

Category winners + On the Horizon

ModelInput 0 — $10Output 0 — $50
Input$2
Output$10
Input$4
Output$20
Input$10
Output$50
Input$10
Output$50

Each column has its own scale. Standard uncached input and output rates; short-context pricing where applicable.

Input is what you send; output is what the model generates, including billable thinking. More thinking can mean more tokens at the same rate. These are API costs, not monthly subscriptions or a price per completed task.

Sources, thinking levels & pricing details

Compare standard paid API access. Caching, batch discounts, fast service, regional routing, tool fees and taxes can change the bill. Coding tools may add their own charges. Low, medium and high thinking are provider-specific settings, not comparable amounts of reasoning.

Gemini 3.8 Flash

Paid standard introductory rate through December 31, 2026; scheduled to become $1.50 input / $7.50 output on January 1, 2027. Output includes thinking tokens.

Provider pricing ↗Checked 2026-09-26

GPT-6 Sol

Standard rate for prompts up to 272K input tokens. Above 272K, the full request costs 2× the input rate and 1.5× the output rate. Low, medium and high reasoning share these token rates; extra reasoning adds billable output tokens.

Provider pricing ↗Checked 2026-09-26

Claude Opus 5.5

Global standard rate across the supported context window. Low, medium and high effort share these token rates; thinking adds billable output. Fast mode costs extra.

Provider pricing ↗Checked 2026-09-26

GPT-5.6 Sol

Promotional standard short-context rate, available at least through November 21, 2026. Above 272K input tokens, the full request costs 2× input and 1.5× output. Thinking adds billable output tokens.

Provider pricing ↗Checked 2026-09-26

Claude Opus 5

Global standard rate across the supported context window. Thinking is included in billed output; fast mode costs extra.

Provider pricing ↗Checked 2026-09-26

Claude Fable 5.1

Global standard rate across the supported context window. Thinking is included in billed output; effort changes token use, not this rate.

Provider pricing ↗Checked 2026-09-26

GPT-6 Astra

Standard rate for prompts up to 272K input tokens. Above 272K, the full request costs 2× the input rate and 1.5× the output rate. Low, medium and high reasoning share these token rates; extra reasoning adds billable output tokens.

Provider pricing ↗Checked 2026-09-26

Thinking billing: OpenAI · Anthropic · Google

The watchlist

On the Horizon

New announcements we’re following. A confirmed launch is not a recommendation: independent comparisons and BMN’s category reviews still matter.

Aleph AlphaAwaiting BMN review

Kolibri

Announced Oct 3, 2026

Aleph Alpha released Kolibri, an Apache-2.0 open-weight English/German MoE with 78.1B total parameters, 3.46B active per token and support for up to a 1M-token context. Aleph Alpha reports 96.9 on AIME 2025 and 85.9 on LiveCodeBench v6; these are vendor-run claims, not a BMN quality verdict.

What we’re checking

Seek independent exact-version coding and agent comparisons and a practical BMN-accessible inference route. Official requirements start around datacenter-class hardware, so local hands-on BMN testing is not yet assumed. Reassess vendor access options, third-party hosting and independent results by October 7.

Original announcement ↗

Source checked Oct 5, 2026 · Next review target Oct 7, 2026

Black Forest LabsAwaiting BMN review

FLUX 3 Image

Announced Oct 1, 2026

Black Forest Labs released the image-generation and editing endpoint of FLUX 3 on October 1. Public API and playground access, up to ten references, bounding-box composition and up to 4K output are documented. These are supplier claims, not a BMN quality verdict.

What we’re checking

October 4 official release notes, Kingy launch article, Creative AI News pixel audit and Fuser comparison checked. FLUX3 registered47820. New sources321/322 approved for methods/discovery only: vendor-selected samples, mixed sizes/dates, few trials and unresolved relationships prevent independent corroboration. No supported new order for editing, artistry or photography. Seek matched independent tests; recheck by October6.

Original announcement ↗

Source checked Oct 4, 2026 · Next review target Oct 6, 2026

GoogleAwaiting BMN review

Gemini 4 Argon

Announced Sep 30, 2026

Google announced Gemini 4 Argon for complex long-horizon coding, enterprise knowledge work and cyber defense. Access is currently limited to trusted cyber defenders through the Fairwind Program; Google says broader developer, enterprise and consumer access will follow. Vendor performance claims remain attributed.

What we’re checking

October4 official announcement, Gemini API changelog and Arena listing checked. Access remains restricted to trusted Fairwind users; exact generally usable API configuration is not verified. Arena listing does not establish production access. No writing screen is eligible yet. Reassess by October6.

Original announcement ↗

Source checked Oct 4, 2026 · Next review target Oct 6, 2026

AnthropicEvaluation in progress

Claude Sonnet 5.5

Announced Sep 28, 2026

Anthropic announced Claude Sonnet 5.5 on September 28, 2026. The public API model is claude-sonnet-5-5; vendor capability claims remain attributed and do not establish a BMN ranking.

What we’re checking

October4 official page, Vals, CodeRabbit, Flavio and AI Coding Daily checked. API High vs Claude Code Medium defaults and external High/Max harnesses kept separate. Writing results reused: Fiction screened out; Screenwriting suite82 processed, no approval pending. Replit Power configuration47823 now registered, untested. No supported coding podium displacement; need second matched comparative publisher. Reassess by October6.

Original announcement ↗

Source checked Oct 4, 2026 · Next review target Oct 6, 2026

Alibaba / QwenAwaiting BMN review

Qwen-Image-2.1

Announced Sep 20, 2026

Qwen released Qwen-Image-2.1, a downloadable unified image-generation and editing model with a 7B visual generation component, native RGBA transparency, local editing, and support for up to 10 reference images. The default weights use the Qwen Research License, so commercial use requires separate licensing.

What we’re checking

Treat as a distinct editing/open-weight branch rather than a chronological successor to Qwen-Image-3.0-Pro. Seek current independent comparisons for image quality, editing precision, reference identity and transparent-asset workflows before considering any BMN placement.

Original announcement ↗

Source checked Oct 5, 2026 · Next review target Oct 7, 2026

StepFunAwaiting BMN review

Step 5 Preview

Announced Sep 20, 2026

StepFun's official platform lists Step 5 Preview with public API access. Independent sources report a 600B-total/27B-active MoE, 1M context and $1.00/$2.70 per-million-token pricing, but BMN will keep those claim-level details separate until they are verified against readable first-party documentation.

What we’re checking

Seek exact-version independent coding/agent comparisons and verify StepFun's promised open-weight release around October 15. The model is now registered as a preview coding contender; no BMN ranking change is implied.

Original announcement ↗

Source checked Oct 5, 2026 · Next review target Oct 7, 2026

Stay current

Know when the recommendations change.

Meaningful AI updates, plus On the Horizon: new releases we’re watching. About once a week. Only when there’s something worth sharing.

What changed
September 26, 2026

Opus 5.5 High enters the coding podium.

Today’s external-evidence review puts Claude Code + Opus 5.5 High first in Best Coding Overall and Code Generation, and second in Agentic Coding. These early recommendations carry an asterisk and a two-day review cycle. Exact effort settings, contrary results, and test limitations remain visible. Coding reviews proceed independently of pending writing approvals.

September 25, 2026

Clear recommendations. Reasons you can inspect.

Image and video reviews now support explicit first, second and third places, with category-specific criteria and published tiebreak decisions. Photorealism covers everyday phone snapshots as well as professional photography. Confidence and evidence gaps remain visible alongside our recommendations.

September 22, 2026

Image and video evidence, with its limits.

New source observations identify tested variants, task-specific findings, and conflicts with existing recommendations. They appear separately from the evidence behind the older rankings. Generic video summaries now receive the same provisional treatment as image summaries; scores and ranking-verification dates remain unchanged.

September 21, 2026

Clearer comparisons. Evidence you can inspect.

Larger text, direct category links, and expandable comparisons make the rankings easier to use. Evidence gaps are now visible, including inherited image placements awaiting version-specific confirmation. Ranking order and verification dates have not been advanced by this presentation update.

September 10, 2026

ChatGPT Images 2.5 replaces GPT Image 2.

OpenAI’s new image release adds faster generation, stronger subject preservation, more reliable multi-turn edits, and new direct-editing tools. The release initially inherited GPT Image 2’s placements. Those inherited placements are provisional until version-specific comparative evidence is documented. GPT-6 Astra’s access and API pricing have also been brought up to date.

September 8, 2026

Coding now ranks tested configurations.

Every Coding result identifies the system, underlying model or platform-selected AI, access plan, system version, and test date. Technical awards cleared the first supervised sweep; Builder awards are provisional until the full Practical Consensus threshold is met.

Methodology

Evidence in.
A useful answer out.

We assess outside findings for the task and tested configuration. No single benchmark, arena, reviewer, or company determines a winner. These weights apply when comparable evidence supports scored rankings. Image and video use ranked editorial recommendations with explicit tiebreakers, confidence and evidence limitations; they have no numerical scores. Builders use a separate profile: 20% working-product proof, 60% practitioner consensus, 10% ownership and publishing, and 10% ease and value.

Read the full methodology →
Quality

Category performance

Judge the task: artistic expression, photographic believability, motion, or editing precision.

Evidence

Comparisons that fit

Blind arenas and practitioner comparisons inform the decision, with exact versions and task limits preserved.

Tiebreaks

A clear order

Consistency, instruction fidelity, creative control, breadth, then a documented editorial judgment.

Buying advice

Price & access

Separate from quality-specialty ordering. Best Overall considers practical workflow and value after quality.

Confidence

Limits in view

A recommendation can be useful without being indisputable. We explain close calls and missing comparisons.

Gate

Complete candidate pool

Every contender in the defined, dated evaluation field must be evaluated. New discoveries enter through an eligibility review.