01 Monthly rankings

LLM Rankings 2026

Claude Fable 5, GPT-5.6 Sol, Claude Opus 5, GPT-5.5, Gemini 3.1 Pro and the open-weight GLM-5.2 — compared on agentic benchmarks, prices and real scenarios.

Updated: Aug 16, 2026Method: agentic benchmarks + independent evalsNext update: September 2026

TL;DR — which model for what (August 2026)

  • Maximum capability: Claude Fable 5 — the first public Mythos-class model, 80.3% SWE-Bench Pro, 1M context; $10/$50 per million tokens.
  • Terminal & agents: GPT-5.6 Sol — 88.8% Terminal-Bench 2.1, 91.9% in Ultra mode; Terra and Luna tiers cost far less.
  • Everyday work: Claude Opus 5 — near Fable at half the price ($5/$25), effort dial low→xhigh.
  • Your own perimeter: GLM-5.2, DeepSeek V4, Llama 4 — open weights; the gap to the frontier is measured in months.
1

Claude Fable 5

Anthropic · Mythos-class · Jun 9, 2026
1M ctx$10 / $50 per 1MAdaptive Thinking
80.3SWE-Bench Pro

The first publicly available Mythos-class model — a tier above the entire Opus line. Record on SWE-Bench Pro: 80.3% versus 69.2% for Opus 4.8 and 58.6% for GPT-5.5. Output up to 128K tokens — roughly a hundred pages of code or documentation in one response. The release quirk: conservative safety classifiers route cybersecurity, biology, chemistry and distillation queries to Opus 4.8 — triggering in under 5% of sessions, with the substitution disclosed. Historical footnote: the release survived a government pause and returned to general access on July 1.

80.3%SWE-Bench Pro
1MContext
128KOutput
$10/$50per 1M tokens
Long autonomous workHard code2× Opus 5 priceFallback to Opus 4.8
2

GPT-5.6 Sol

OpenAI · Jul 9, 2026
1.05M ctx$5 / $30 per 1MSol · Terra · Luna
88.8Terminal-Bench 2.1

The flagship of a three-tier family: Sol, Terra ($2.50/$15) and Luna ($1/$6). Best public result in terminal-agentic work — 88.8% on Terminal-Bench 2.1, with Sol Ultra mode reaching 91.9%, ahead of even the restricted Claude Mythos 5 (88.0%). The launch was unprecedented: at the U.S. government's request, access first went to vetted partners only. Strengths — command line, browsing, long tool chains.

88.8%TB 2.1 (Sol)
91.9%TB 2.1 (Ultra)
1.05MContext
$5/$30per 1M tokens
Terminal & agentsThree price tiersRestricted at launch
3

Claude Opus 5

Anthropic · Jul 24, 2026
1M ctx$5 / $25 per 1MEffort dial
43.3Frontier-Bench · #1

The workhorse of the new line: close to Fable 5 on most tasks at half the price. New state-of-the-art on Frontier-Bench (43.3% versus Fable's own 33.7%) and GDPval-AA. The effort dial — low / medium / high / xhigh — trades cost against capability per request; at lower levels the model keeps most of its performance while burning far fewer tokens. Default model on the Max plan; per Anthropic, the most misuse-resistant Opus yet.

43.3%Frontier-Bench
1MContext
$5/$25per 1M tokens
4Effort levels
Price / qualityEveryday workCode & knowledge
4

GPT-5.5

OpenAI · April 2026
1M ctx$5 / $30 per 1MPro: $30/$180
82.7Terminal-Bench 2.0

OpenAI's previous flagship remains a strong generalist: 82.7% on Terminal-Bench 2.0, 81.8% on CyberGym. Against the Mythos class it visibly trails on hard agentic code — 58.6% SWE-Bench Pro versus Fable 5's 80.3%. The Pro tier ($30/$180) adds accuracy on critical work. A sensible pick when your processes are already built around the OpenAI ecosystem.

82.7%TB 2.0
58.6%SWE-Bench Pro
1MContext
$5/$30per 1M tokens
GeneralistEcosystemTrails on agentic code
5

Gemini 3.1 Pro

Google DeepMind · Feb 19, 2026
Deep ThinkFlash 3.5/3.6 nearbyVertex AI
ProGoogle flagship

The top of Google's line: 3.1 Pro for deep reasoning, Deep Think for the hardest problems, Flash 3.5 and 3.6 as the fast cheap layer for agent loops. Strengths — multimodality and ecosystem integration (Workspace, Vertex, Search). Fewer public results on cross-vendor agentic benchmarks than Anthropic or OpenAI, hence the dash in our table — missing data, not weakness.

MultimodalityGoogle ecosystemFew public agentic scores
6

GLM-5.2

Z.ai · Open Source
Open weightsSelf-hosted
OSSOpen leader

The strongest open challenger to flagship level per independent comparisons this summer. Its open-source company: DeepSeek V4 (April 2026) competes on API price, Llama 4 Scout holds the context record — 10 million tokens. Open-weight developers themselves estimate the gap to the closed frontier in months, not generations. The usual price applies: your own GPU perimeter and engineering — in exchange, data never leaves your infrastructure. Full comparison in our open-vs-closed guide.

Data stays insideCost = hardware onlyNeeds own infrastructure
01.1 —

Comparison Table

LLM comparison, August 2026
ModelCompanyReleaseHeadline benchmarkContext$/1M (in/out)
Claude Fable 5AnthropicJun 9, 26SWE-Bench Pro — 80.3%1M10 / 50
GPT-5.6 SolOpenAIJul 9, 26Terminal-Bench 2.1 — 88.8%1.05M5 / 30
Claude Opus 5AnthropicJul 24, 26Frontier-Bench — 43.3% (#1)1M5 / 25
GPT-5.5OpenAIApr 26Terminal-Bench 2.0 — 82.7%1M5 / 30
Gemini 3.1 ProGoogleFeb 19, 26n/aVertex rates
GLM-5.2Z.ai · OSS2026open weightsself-hosted

How to read the table. The "headline benchmark" column shows each model's best publicly confirmed result: SWE-Bench Pro — autonomous engineering in large repositories, Terminal-Bench — command-line work, Frontier-Bench — long office tasks. A dash means no public agentic data, not weakness. Context is a question of your documents: email fits in 128K, contracts want a million. Prices are per million tokens in/out; every vendor charges several times more for output.

"Headline benchmark" is each model's best publicly confirmed result; no single test has been publicly passed by all six as of August 2026. Sources: Anthropic and OpenAI announcements, Vellum, Vals AI, Artificial Analysis. Updated Aug 16, 2026.

01.5 —

Prices in Practice

A "$10 per million tokens" sticker says little until translated into tasks. Real volumes at August rates: a support chatbot — a typical dialogue runs 12 messages, about 4,000 tokens with knowledge-base context; a thousand dialogues a month is 4M input tokens: $20 on Claude Opus 5 or GPT-5.5, $40 on Fable 5, $4 on GPT-5.6 Luna. A 150-page contract analysis: ~110K input tokens — $0.55 per document on Opus 5 and $1.10 on Fable 5, versus an hour of a lawyer's time. Summarizing 500 emails daily: 2.5M tokens a month — from $2.50 on Luna to $25 on Fable.

The hidden line items people discover in month two. Output tokens cost several times more than input: $25–50 per million on flagships versus $5–10 in — generating long reports hurts the budget more than reading long documents. Reasoning bills by tokens actually "thought", and Fable 5's Adaptive Thinking never switches off — a hard question can cost several times a simple one at identical answer length. Re-sending the whole context with every message remains the chief budget-eater of chatbots; prompt caching, discounted up to 90% by flagship APIs, is the cure.

A budget anchor for teams up to 20 people: $100–300 a month in API fees covers assistants, document analysis and summarization without rationing. If the bill grows faster than the value — check caching and context length first, model choice second.

01.6 —

A Note on Switching Costs

One number worth knowing before committing to any vendor: in our reader survey, teams that kept prompts, evaluation sets and data pipelines separate from vendor SDKs reported switching models in days; teams that built directly against one API reported weeks and, in two cases, gave up entirely. The leaderboard above has changed order twice in twelve months — architecture that treats the model as a replaceable part is not paranoia, it is the base case.

01.3 —

How We Test

Since summer 2026 the familiar composite of MMLU, GPQA and HumanEval has been retired: classic tests are saturated, with flagships separated by fractions of a point. The ranking now rests on agentic benchmarks — SWE-Bench Pro (real engineering tasks in large repositories), Terminal-Bench 2.1 (autonomous command-line work), Frontier-Bench and GDPval-AA (long office work). Where the numbers come from: official vendor announcements cross-checked against independent trackers — Vals AI, Vellum, Artificial Analysis, Endor Labs. Discrepancies get flagged in the text: per Endor Labs, record-holder Fable 5 landed mid-table on safe vulnerability-fixing (59.8% FuncPass) despite outstanding official scores elsewhere — such gaps are not scandal but a normal property of young benchmarks.

Separately, a manual set of 14 working tasks that exist in no public benchmark: a 500-page contract with risks buried mid-document, a legacy code migration, a spreadsheet full of dirty data, a client email in three languages. These runs are more subjective but closer to reality — their results feed the long-form blog reviews, not the headline score.

Found a discrepancy with our numbers? Write to [email protected] — we re-check and correct publicly. That is the corrections policy at work.

01.4 —

Choosing by Scenario

The abstract "best AI" is a question without an answer. The right question is: best for what? Six situations from our practice:

Legal

200+ page contracts, expensive mistakes

Claude Fable 5 or Opus 5: the million-token context and the best results on long autonomous work. Opus 5 gives the same 1M at half the price; Fable is for when mistakes cost the most.

Startup

Support chatbot on a budget

Claude Sonnet 5 or GPT-5.6 Terra ($2.50/$15): on routine tickets customers will not notice the difference from flagships, and the API bill is several times lower. Bring in a flagship only for escalations.

Bank

Personal data, regulators, audits

Open-weight GLM-5.2, DeepSeek V4 or Llama 4 on your own GPUs — data never leaves the perimeter. Cloud is acceptable only on enterprise tiers with a contractual no-training clause.

Media

Trends, breaking news, social

Grok 4.3 as the second model for real-time X data; writing and editing — Claude Opus 5 or GPT-5.6. No single model replaces this combination.

Video

Meeting recordings, lectures, streams

The Gemini line: 3.1 Pro and Deep Think for deep analysis, Flash 3.5/3.6 for volume. Native video and the Google ecosystem remain their home turf.

Volume

Cheap mass operations: tagging, classification, digests

GPT-5.6 Luna at $1/$6, junior Claude tiers, or open models via inference providers. Price per token wins here, not benchmark percentages.

A separate tip for teams choosing their first model: skip the month-long bake-off. Take the three tasks that eat most of your time, run them through two or three APIs within a week, and count two things — how many edits each answer needs and what a thousand such requests cost. That homemade test predicts your experience better than anyone's leaderboard, including ours.

The 80/20 rule: start with a cheap model and upgrade only where mistakes are genuinely expensive. The reverse path — "take the most powerful, optimize later" — almost always ends in an unoptimized API bill.
01.2 —

FAQ

What is the best AI model in August 2026?
Depends on the job. The most capable public model is Claude Fable 5 (Mythos-class, 80.3% SWE-Bench Pro). GPT-5.6 Sol leads terminal-agentic work (88.8% Terminal-Bench 2.1). Claude Opus 5 wins on everyday price-performance. Self-hosted — GLM-5.2 or Llama 4. The abstract "best" no longer exists — a sign of a maturing market.
Which model for a small business?
Claude Sonnet 5, GPT-5.6 Terra ($2.50/$15) or Luna ($1/$6): near-flagship quality on routine tasks at a fraction of the bill. Fable 5 and Opus 5 pay off where errors are expensive: contracts, analysis, critical code.
How do open-source models compare?
Open-weight developers themselves put the gap to the closed frontier at months, not generations. GLM-5.2 is called the strongest open challenger to Fable 5; DeepSeek V4 competes on price. The infrastructure difference remains: you need your own GPU perimeter — in return, data never leaves it.
Where are the Chinese and Russian models?
Chinese models are already in: GLM-5.2 leads the open tier and DeepSeek V4 features in the overview. GigaChat and YandexGPT get blog coverage; models enter the main table once they have public agentic-benchmark results and a stable API.
Why do the models show different benchmarks in the table?
Because no single public test has been passed by all six models as of August 2026. We show each model's best confirmed headline result and print an honest dash where no public data exists — more informative than an artificial composite score.
How often are rankings updated?
Monthly. For major releases (new Claude, GPT, Gemini) — an unscheduled update within 48 hours including an independent test run.