Current AI rankings

Best AI for Writing

The winners, the alternatives, and why we chose them.

The one to beat

Best Writing Overall

Winner · #1

Claude Fable 5.1

Anthropic

Long-form writing, distinctive voices and demanding revisions

API$10 in $50 out per 1M tokens
Weighted score: 91.5
Why it wins & tradeoffs

Our first choice for nuanced prose, following instructions and revising long-form work.

Price & access
Claude subscription and API; premium API cost
Watch out for
Premium cost makes high-volume drafting expensive.
Content 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)
  • LMArena leaderboardSource page · Observed Sep 12, 2026

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

  • 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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Sep 12, 2026Provider, pricing & access ↗
2

GPT-6 Astra

OpenAI

Professional documents and structured revisions

Weighted score: 90.0
When to choose GPT-6 Astra

A close alternative with concise writing, factual discipline and lower evaluated-task costs.

API$10 in $50 out per 1M tokens
Price & access
ChatGPT Work and API; access remains plan-dependent
Watch out for
May be less consistent at producing a distinctive narrative voice.
Content 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)
  • 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.

  • 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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Sep 12, 2026Provider, pricing & access ↗
3

Claude Opus 5

Anthropic

Polished long-form prose and careful editing

Weighted score: 85.8
When to choose Claude Opus 5

Strong prose and editing judgment, but higher cost keeps it behind Astra overall.

API$5 in $25 out per 1M tokens
Price & access
Claude subscription and API; premium pricing
Watch out for
High-volume drafting can be expensive.
Content 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%.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Sep 12, 2026Provider, pricing & access ↗
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
What we judge

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

Writing qualityInstruction controlRevision strengthLong-form coherenceAccess & reliability
Winner · #1

Claude Fable 5.1

Anthropic

Strategy memos, proposals and executive briefs

API$10 in $50 out per 1M tokens
Weighted score: 91.0
Why it wins & tradeoffs

Our first choice for nuanced, persuasive documents, supported by strong knowledge-work test results.

Price & access
Claude subscription and API; premium API cost
Watch out for
Premium cost may be hard to justify for routine copy.
Content 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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Sep 12, 2026Provider, pricing & access ↗
2

GPT-5.6 Sol

OpenAI

Everyday documents, presentations and high-volume drafting

Weighted score: 90.0
When to choose GPT-5.6 Sol

A close second for polished documents and presentations at lower cost.

API$4 in $20 out per 1M tokens
Price & access
ChatGPT and API; lower token pricing than Astra
Watch out for
For especially sensitive or persuasive documents, Fable may be the better choice.
Content restrictions
Moderate
Evidence
Artificial Analysis's AA-Briefcase favors GPT-5.6 Sol for presentation quality. Access and lower cost also contribute to its rank.
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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Sep 12, 2026Provider, pricing & access ↗
3

GPT-6 Astra

OpenAI

Structured documents, analysis and revision

Weighted score: 89.8
When to choose GPT-6 Astra

Strong structure, reasoning and document revision; Sol narrowly wins on the combined practical factors.

API$10 in $50 out per 1M tokens
Price & access
ChatGPT Work and API; access remains plan-dependent
Watch out for
Access depends on your plan; persuasive voice may be less polished than the leader's.
Content 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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Sep 12, 2026Provider, pricing & access ↗
What we judge

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

Clarity & structurePersuasionTone controlFactual disciplineRewriting
Winner · #1

Claude Fable 5.2

Anthropic

Original short fiction

APIWeighted score: 100.0Provisional: evidence still developing
Evidence limitations

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

Why it wins & tradeoffs

Placed #1 among 4 models in BMN's two-round blind test, judged by an AI panel and approved by the owner. Results may vary by genre and prompt.

Price & access
Check Anthropic for current API and subscription access.
Watch out for
These tests cover short fiction, not a complete novel.
Evidence
BMN test 197: 8 of 8 ranking points across two equally weighted prompts. Ties went to the model closest to the requested word counts across both prompts.
Ranking last verified: Nov 12, 2026Provider, pricing & access ↗
2

Kimi K3.1 Pro

Moonshot AI

Original short fiction

Weighted score: 62.5Provisional: evidence still developing

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

When to choose Kimi K3.1 Pro

Placed #2 among 4 models in BMN's two-round blind test, judged by an AI panel and approved by the owner. Results may vary by genre and prompt.

Price & access
Check Moonshot AI for current API and subscription access.
Watch out for
These tests cover short fiction, not a complete novel.
Evidence
BMN test 197: 5 of 8 ranking points across two equally weighted prompts. Ties went to the model closest to the requested word counts across both prompts.
Ranking last verified: Nov 12, 2026Provider, pricing & access ↗
3

Claude Opus 5.5

Anthropic

Original short fiction

Weighted score: 62.5Provisional: evidence still developing
When to choose Claude Opus 5.5

Placed #3 among 4 models in BMN's two-round blind test, judged by an AI panel and approved by the owner. Results may vary by genre and prompt.

API$4 in $20 out per 1M tokens
Price & access
Check Anthropic for current API and subscription access.
Watch out for
These tests cover short fiction, not a complete novel.
Evidence
BMN test 197: 5 of 8 ranking points across two equally weighted prompts. Ties went to the model closest to the requested word counts across both prompts.
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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Nov 12, 2026Provider, pricing & access ↗
What we judge

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

Prose qualityCharacter voiceNarrative controlOriginalityRewriting
Winner · #1

GPT-6 Astra

OpenAI

Original screenplay scenes

API$10 in $50 out per 1M tokens
Weighted score: 87.5Provisional: evidence still developing
Why it wins & tradeoffs

Placed #1 among four models in BMN's two-round blind test, judged by an AI panel and approved by the owner. Results may vary by genre and prompt.

Price & access
OpenAI subscription or API; check current plans.
Watch out for
These tests cover individual scenes, not a complete feature screenplay.
Content restrictions
Moderate
Evidence
BMN test 138: 7 of 8 ranking points across two equally weighted prompts. Ties were settled by the owner.
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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Oct 26, 2026Provider, pricing & access ↗
2

GPT-6.1 Sol

OpenAI

Original screenplay scenes

Weighted score: 87.5Provisional: evidence still developing

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

When to choose GPT-6.1 Sol

Placed #2 among four models in BMN's two-round blind test, judged by an AI panel and approved by the owner. Results may vary by genre and prompt.

Price & access
Check OpenAI for current API and subscription access.
Watch out for
These tests cover individual scenes, not a complete feature screenplay.
Evidence
BMN test 138: 7 of 8 ranking points across two equally weighted prompts. Ties were settled by the owner.
Ranking last verified: Oct 26, 2026Provider, pricing & access ↗
3

GPT-6 Sol

OpenAI

Original screenplay scenes

Weighted score: 50.0Provisional: evidence still developing
When to choose GPT-6 Sol

Placed #3 among four models in BMN's two-round blind test, judged by an AI panel and approved by the owner. Results may vary by genre and prompt.

API$2 in $10 out per 1M tokens
Price & access
Check OpenAI for current API and subscription access.
Watch out for
These tests cover individual scenes, not a complete feature screenplay.
Evidence
BMN test 138: 4 of 8 ranking points across two equally weighted prompts. Ties were settled by the owner.
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.

Review dates may differ from publication dates. Some links lead to a source page rather than an individual test.

Ranking last verified: Oct 26, 2026Provider, pricing & access ↗
What we judge

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

Dialogue & subtextScene constructionPacingCharacter voiceFormatting & revision

Small score gaps are close calls. Media rankings are editorial. How we compare →

Know when the recommendations change.

Meaningful AI updates, plus On the Horizon: new releases we’re watching. Tuesdays at 9 a.m. Pacific, when there’s something worth sharing.

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$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

On the Horizon

New models still being assessed. Each status shows what needs to happen next; completed reviews have their own record.

Completed reviews & decisions →

OpenAIGathering comparison evidence

GPT-6.2 Astra

Announced Nov 17, 2026

GPT-6.2 Astra is available in Work, Codex and the API. OpenAI attributes improved coding and professional workflows to this release; independent category assessment is pending.

Next step & review dates

Obtain exact-configuration independent hands-on comparisons alongside current benchmarks. Writing screens require category-specific external qualification and budget capacity; no paid screen authorized by registration.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

OpenAIGathering comparison evidence

GPT-6.2 Sol

Announced Nov 17, 2026

GPT-6.2 Sol is available in Work, Codex and the API. OpenAI attributes improved coding and professional workflows to this release; independent category assessment is pending.

Next step & review dates

Obtain exact-configuration independent hands-on comparisons alongside current benchmarks. Writing screens require category-specific external qualification and budget capacity; no paid screen authorized by registration.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MicrosoftGathering comparison evidence

MAI-Code-2

Announced Nov 17, 2026

Microsoft confirms public GitHub Copilot availability for MAI-Code-2. The registered coding configuration uses Copilot CLI Max; build is not disclosed in the launch evaluation.

Next step & review dates

Obtain independent original repository comparisons on Copilot CLI Max with build, attempts, interventions and complete costs. Microsoft MSBench comparisons are vendor claims and promotional pricing is not stable per-task cost.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MicrosoftGathering comparison evidence

MAI-Code-2-Flash

Announced Nov 17, 2026

Microsoft confirms GitHub Copilot availability and limited Microsoft Foundry preview for MAI-Code-2-Flash. Copilot CLI Max is registered distinctly from other routes.

Next step & review dates

Seek independent matched Copilot CLI Max comparisons; do not transfer Code2 or Code1.1Flash scores. Vendor frontend preference study and discounted prices alone do not establish comparative coding reliability.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MicrosoftGathering comparison evidence

MAI-Image-2.7

Announced Nov 17, 2026

Microsoft released MAI-Image-2.7 in Microsoft Foundry public preview on November17. This release is tracked distinctly from the October preview. Microsoft advertises generation and editing with transparency support.

Next step & review dates

Match exact November17 output to independent repeated photo, typography, artistry and same-source editing comparisons. Do not transfer October preview rankings or vendor claims. Separate standard and Flash routes.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MicrosoftGathering comparison evidence

MAI-Image-2.7-Flash

Announced Nov 17, 2026

Microsoft released the Flash variant of MAI-Image-2.7 in Foundry public preview on November17. Microsoft advertises a lower-cost faster option, also used in Canvas.

Next step & review dates

Seek original same-input standard-versus-Flash and incumbent comparisons with native resolution, repeat attempts, latency, failure cases and financial disclosures; no ranking inference from release pricing.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

AlibabaGathering comparison evidence

Qwen4-Max

Announced Nov 16, 2026

Alibaba released production Qwen4-Max for text output and multimodal understanding. The qwen4-max API defaults to High effort; it is distinct from qwen4-max-preview.

Next step & review dates

Production model docs recovered after press-page access failed. Atomic Agent's three runs on one59-test repo and CodeRouter's175Python tasks are narrow and use different harnesses/retry caps. Replicate production High on multiple repositories; seek approved production-specific writing evidence before paid work.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MeituanGathering comparison evidence

LongCat-Video-Avatar 1.6

Announced Nov 15, 2026

Published weights and CUDA commands support audio-driven text/image-conditioned single- and multi-character video. Seek matched lip sync, role separation, identity drift and elapsed compute versus another audio-driven system.

Next step & review dates

Published weights and CUDA commands support audio-driven text/image-conditioned single- and multi-character video. Seek matched lip sync, role separation, identity drift and elapsed compute versus another audio-driven system.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

inclusionAIGathering comparison evidence

Ling 3.2 Flash

Announced Nov 13, 2026

Ant Ling documents its native Nov5 launch and temporary free access. OpenRouter lists a separate Nov13 rate-limited Ant Digital route with 1M context and text/image input. Original browser coding trial is scoped to its own harness; no writing quality conclusion.

Next step & review dates

Ant’s native launch was Nov5; OpenRouter’s distinct free route lists Nov13. Original four HTML tasks on the exact free route (thinking off) returned a turret error and an upstream timeout. Seek a dated fiction result or original screenplay comparison, separately; this coding task qualifies neither.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Alibaba QwenGathering comparison evidence

Qwen4-Max-Preview

Announced Nov 11, 2026

Alibaba released a fixed Qwen4-Max-Preview checkpoint through Token Plan, with default xhigh thinking and a1M context. The preview window runs November11–25; dedicated Token Plan credentials are required.

Next step & review dates

The production qwen4-max launched Nov16 as a separate endpoint. Preview Token Plan expires Nov25 (UTC+8). Do not transfer production Atomic Agent 0.7.0 or CodeRouter results; track retirement or an exact preview comparison.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

BaiduGathering comparison evidence

ERNIE-Light-DT-1.0

Announced Nov 10, 2026

Distinct baidu/ernie-light-dt-1.0-intl endpoint served by Baidu Qianfan, separate from ERNIE 5.5 Flash Preview. Seek dated exact-route writing-specific observations; no paid screen until qualified.

Next step & review dates

Distinct baidu/ernie-light-dt-1.0-intl endpoint served by Baidu Qianfan, separate from ERNIE 5.5 Flash Preview. Seek dated exact-route writing-specific observations; no paid screen until qualified.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

AnthropicAwaiting public access

Claude Mythos 5.2

Announced Nov 9, 2026

Anthropic announced Mythos 5.2 for verified organizations. Access is restricted.

Next step & review dates

Verify authorized access to an exact usable production configuration before evaluating it. Fable’s API availability and writing tests do not establish Mythos eligibility or quality.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

ByteDanceGathering comparison evidence

Seedream 5.5

Announced Nov 9, 2026

ByteDance introduced Seedream 5.5 for image generation and editing. Dreamina documents the Image 5.5 selector for eligible accounts; ByteDance reports native transparency and improved preservation across successive edits.

Next step & review dates

Saybrush Nov11 kie API 1.5K PNG chains show subject preservation in successive wardrobe and scene edits. One commercial host, selected examples, no same-input rivals. Compare native exact setting on repeated edits, alpha, small text and unedited regions against incumbents.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

OpenAIAwaiting public access

GPT-6 Cyber

Announced Nov 5, 2026

OpenAI’s November 5 security model is initially limited to selected approved Daybreak Red customers. Vendor cyber evaluations are not a general coding ranking.

Next step & review dates

Confirm eligible access and exact harness/effort before registering a rankable coding configuration. No general writing screen warranted.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

GoogleGathering comparison evidence

Gemini Omni 1.2 Flash

Announced Nov 5, 2026

Google released Omni 1.2 Flash with native 15-second generation and editing at $0.07/second for 720p. Arena's preliminary text-to-video board puts it first; this is not a BMN overall quality verdict.

Next step & review dates

CellCog's original11-task comparison shows promising lifelike dialogue but API restrictions changed four tasks and older competitor clips were reused; publisher sells competing generation. Audio-inclusive AA preferences are not picture-only quality. Obtain repeated same-footage edits with faces/background preserved and matched instructions.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Thinking Machines LabAwaiting testing access

Inkling 2 Small

Announced Nov 5, 2026

Thinking Machines' Nov12 update and public HF model upload confirm Inkling2Small weights are now available under Apache2.0, with additional hosting and runtime integrations. Vendor benchmarks remain claims; this access change does not release saved BMN writing holds.

Next step & review dates

Nov12 official update and HF upload verify Apache2 weights released; access metadata changed. Saved writing holds45/46 remain until a compliant unchanged-target exact route passes a documented availability decision. Then external category qualification and $5 reservations still apply. Coding comparisons of Tinker256K/OpenCode/other hosts remain distinct.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MeituanAwaiting testing access

LongCat-2.5

Announced Nov 2, 2026

Meituan's final LongCat-2.5 API is available, distinct from September's preview; MIT weights and native API documentation were verified November11. Vendor benchmarks use several harnesses and do not independently establish comparative quality.

Next step & review dates

Native API/docs and TOKRACE creative examples checked; mechanical/diagram errors and useful assets are task-specific, not matched ClaudeCode2.1.280/512K evidence. Obtain exact independent coding and professional-writing comparisons. Native BMN credential unverified; any future creative screen also requires external category qualification and budget eligibility.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

PikaGathering comparison evidence

Pika H3 Flex

Announced Oct 29, 2026

Pika released H3 Flex with native 480p/768p video and synchronized audio. Its hosted upscaler is separate.

Next step & review dates

Verify repeated native-resolution reference motion and changes to existing footage against Kling and Seedance; separate native detail from upscaling.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

SourcefulGathering comparison evidence

Riverflow 2.6 Pro High

Announced Oct 29, 2026

Sourceful2.6Pro high-effort image configuration verified November12. Delivered custom sizes may include resizing or upscaling; vendor GEditBench preference claims are not independent evidence.

Next step & review dates

Registered47946. Obtain original same-input photo, editing and design comparisons against current field with native-output inspection, effort, repeats, failures and commercial disclosures. No authorized paid internal media testing.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Particle AIGathering comparison evidence

Particle-1

Announced Oct 28, 2026

Vercel lists Particle-1, a coding-focused post-training of DeepSeek V4.1 Flash, on its AI Gateway. Vercel documents use through Codex and other coding clients.

Next step & review dates

Particle’s Oct 28 evaluation used Terminus 2 at Max, 16 runs per task and an assumed 95% cache hit rate. It does not evaluate Codex at the registered default. Next compare the same repositories, retries, correctness, total tokens and cost on that route.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Nanbeige LLM LabGathering comparison evidence

Nanbeige4.3-33B

Announced Oct 24, 2026

The lab released the 33B instruction checkpoint for local inference. The card distinguishes Base and FP8 and documents mini-SWE-agent at the highest thinking setting.

Next step & review dates

Local weights remain available; require category-specific external writing qualification, compliant unchanged-length serving route and conservative budget reservation before any new screen. Coding needs exact mini-SWE-agent2.4.6/preserved-thinking independent repository comparisons.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

NVIDIAAwaiting testing access

Nemotron 3.5 Bolt E4B

Announced Oct 23, 2026

Official Oct23 model card, actual Q4_K_M GGUF file and separate public NVIDIA NIM text endpoint verified Oct24. Local checkpoint documents64K context. Separate from Super VL and Bolt74B; vendor quality claims uncorroborated.

Next step & review dates

Preserve availability holds37/38 and saved work. Original NIM route documentation does not supply the missing NVIDIA credential or establish unchanged-target usability. Release only by documented availability decision, followed by category-specific writing qualification and budget gates. No quality inference.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

TopviewGathering comparison evidence

Topview T1

Announced Oct 21, 2026

Topview T1 is available through paid text, image and omni-reference video API routes. The provider offers 720p and 1080p output. AI Samson’s Oct 22 T1/Seedance 2.5 comparison is one creator’s evidence.

Next step & review dates

The Nov 4 seven-input case demonstrates reference-directed character replacement. Fourteen indexed comparisons are leads, not controlled trials. Obtain original repeat attempts on the same single still and multi-reference inputs against Seedance 2.5 and Kling; retain resolution and funding disclosures.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Black Forest LabsGathering comparison evidence

FLUX 3 Image Klein

Announced Oct 15, 2026

Black Forest Labs released FLUX 3 Image Klein on October15 with public API and license-gated downloadable weights. Distilled16-step and Base50-step CFG3.5 variants are registered separately. The5.6B label covers the image transformer, excluding text encoder and prompt upsampler. Capabilities and speed statements are vendor claims, not a BMN quality verdict.

Next step & review dates

An Oct 16–17 local RTX 5090 comparison gives distilled int8 Klein the edge on short lettering and layouts; Qwen handled long text and some relighting better. Prompt enhancement changed outcomes. Match these tasks on the native BFL API and Base BF16 before assigning either a local result.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

KreaGathering comparison evidence

Krea 3

Announced Oct 15, 2026

Krea announced Krea3 on October15. The native release describes image editing with reference inputs; partner fal also lists a text-to-image route. Native and partner modes, resolutions and Ultra/Fast variants require separate identification. Vendor speed and creative-quality claims are not a BMN verdict.

Next step & review dates

Use the 200-edit hosted blind study for editing tendencies only. Match native Krea 3 Edit versus Ultra/Fast routes and obtain independent evidence for generation and artistry.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

GitHubGathering comparison evidence

GitHub Copilot HydraFusion / Max — October update

Announced Oct 14, 2026

GitHub updated HydraFusion's runtime orchestration and introduced Max on October14. Both remain research previews across Copilot clients. Effort and model selection vary by stage; Max can use extra-high effort. GitHub's capability claims are not a BMN quality verdict.

Next step & review dates

Artificial Analysis tested generally available Fusion Max in Copilot CLI on October 28. Terminal tasks favored Fusion; the overall index and repository questions favored Claude Code Opus Max. Seek independent completed-project evidence with the allowed model pool and intervention history. No transfer to Standard, High or HydraFusion preview.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MetaGathering comparison evidence

Muse Wonder Full

Announced Oct 12, 2026

Meta released Muse Wonder Full on October 12 as a distinct model available to Muse Code subscribers. Official ID muse-wonder-full-1.0; 1M context. Meta documents Power Usage and Maximum subscription access. No public API route was verified. Performance statements are vendor claims, not a BMN quality verdict.

Next step & review dates

c0ze’s Oct17 13-task suite includes Muse Code xhigh; Contributor state not verified. VulcanBench tested Contributor mode and Pat tested goal mode with Contributor off. Obtain mode-matched tasks rather than combining the three.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Z.aiGathering comparison evidence

GLM-Legal

Announced Oct 12, 2026

Z.ai announced GLM-Legal on October 12, built on GLM-5.3-Flash for legal workflows. The vendor describes specialized training and invites applications for a beta, with AutoClaw integration coming later. Performance claims are vendor claims, not a BMN quality verdict.

Next step & review dates

An exact public legal route is now verified: z-ai/glm-5.3-flashx-legal. Verify correspondence to the original beta and compare source-bound legal drafting against incumbents; availability does not establish general business-writing quality.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

JetBrainsAwaiting testing access

Mellum2.1 Thinking

Announced Oct 8, 2026

JetBrains released Mellum2.1, including public Apache-2.0 Thinking weights with 12B total and 2.5B active parameters and 131072-token context. The official model card documents vLLM deployment and thinking settings. Coding improvements are vendor-run results, not a BMN verdict.

Next step & review dates

November11 JetBrains original Hugging Face card confirms BF16 Apache2 weights,131072context and vLLM qwen3/Hermes tooling; vendor Pi0.73.1/114Kcontext evaluation is not independent. No hosted inference provider listed. Next obtain an authorized BMN route or independent exact-runtime repository comparison.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

OpenAIGathering comparison evidence

GPT-6 Sol — October 2026 ChatGPT

Announced Oct 7, 2026

OpenAI released an October 7 GPT-6 Sol snapshot in ChatGPT alongside Intelligent UI. First-party deployment documentation explicitly distinguishes the October ChatGPT model from earlier GPT-6 Sol versions still used in Codex and ChatGPT Work. This chatbot configuration has no BMN quality verdict.

Next step & review dates

Original October7 announcement rechecked November17. Its Intelligent ChatGPT UI remains distinct from old API/Codex and November17 GPT6.2 Sol. Seek an exact UI task comparison; do not transfer newer release benchmarks.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

MicrosoftAwaiting testing access

MAI-Code-1.1-Flash

Announced Oct 7, 2026

Microsoft's October7 update describes downloadable MAI-Code-1.1-Flash with3-bit quantization and256K context, recommending more than120GB RAM; experimental on-device Copilot access is planned by month end. Performance, token-efficiency and price improvements are vendor claims, not a BMN quality verdict.

Next step & review dates

Original Microsoft access documentation rechecked November17. Code1.1Flash remains distinct from today's Code2/Code2Flash. Need the exact selectable client/build/effort and original matched repository comparison; new-release scores cannot be transferred.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Kandinsky LabGathering comparison evidence

Kandinsky 6.0

Announced Oct 6, 2026

Kandinsky Lab released the Kandinsky6.0 video/audio family on October6. Developer documentation describes Lite and Pro variants, five-second synchronized audio/video and optional Full-HD upscaling. Public weights and a fal Pro image-to-video API are documented; these are provider claims, not a BMN quality verdict.

Next step & review dates

In Voyager's Oct 22 native 480p fal trial, Pro preserved the supplied dripper but invented ice in the spill, distorted the title and changed the turntable product. Distinguish text generation from first-frame preservation. Next compare repeated takes on the same prompts at matched resolution; do not transfer results to Lite or the upscaler.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

RekaAwaiting public access

Rho-1

Announced Oct 5, 2026

Reka announced Rho-1, a 19B research preview unifying text, images, video and robotic actions in one network. Reka demonstrates continuous steerable video and describes the system as a proof of concept with limitations. Real-time capabilities are vendor claims; the base model is reported at 0.79× real-time, with faster distilled demonstrations. No BMN quality verdict.

Next step & review dates

Original request-access demonstration page rechecked November17; executable public exact route remains unverified. Confirm permitted usable configuration first; absence of access is not a quality verdict.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Fudan University / Tencent Hunyuan / Zhejiang University researchersGathering comparison evidence

Prism — research preview

Announced Oct 4, 2026

Prism research paper was disclosed October4. Original author-linked MIT preview_alpha (stable) and preview_beta (motion) weights and local CUDA inference instructions were verified October23. These are distinct research-preview configurations, not BMN-tested quality recommendations.

Next step & review dates

Original author GitHub README recovered despite inaccessible arXiv page. Preview alpha/beta checkpoints and CUDA inference support joint video/audio at documented resolutions; no quality test was run. Seek independent identical start-frame, seed, resolution and motion comparisons for each checkpoint.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Aleph AlphaAwaiting testing access

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.

Next step & review dates

Original Apache2 weights and78B/3B-active metadata remain accessible. Hosted BMN writing route remains unverified. Seek original category-specific writing qualification and compliant exact serving route; any new screen also needs shared rolling admission/budget capacity. Vendor scores do not qualify.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

inclusionAIGathering comparison evidence

Ming Image 0.1 Design Layer

Announced Sep 23, 2026

Ant Ling’s Oct27 changelog verifies native API access. Layer takes a flattened image and returns decoupled PNG layers. OpenRouter lists a separate September catalog date; its live serving route was not verified.

Next step & review dates

Native access verified. Compare recovered alpha boundaries, foreground text and background reconstruction against a matched layer workflow.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

inclusionAIGathering comparison evidence

Ming Image 0.1 Design

Announced Sep 22, 2026

Ant Ling’s Oct27 changelog verifies native API access. Design supports prompt-to-image generation for graphic design. OpenRouter lists a separate September catalog date; its live serving route was not verified.

Next step & review dates

Native access verified. Seek original prompt-matched design comparisons for typography, layout and consistency; do not apply layer-edit results.

Original announcement ↗

Source checked Nov 17, 2026 · Next review target Nov 19, 2026

Past ranking and site updates
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.

Evidence in.
A useful answer out.

Task-specific evidence, clear recommendations, and honest limits. Explore our criteria, sources, and how close calls are decided.

Read the full methodology →