Live · 24 models re-ranked after every run

Models change overnight. Your router should know.

AI Stupid Level benchmarks 24 frontier models around the clock and routes every request to whichever one is measurably best right now — for code, reasoning, tool use, speed or cost. One OpenAI-compatible endpoint. Your own provider keys. Zero markup on tokens.

Get your router key →See today’s leaderboard

Free account: every ranking, a 3-model watchlist and 1,000 routed requests a month. No card.

0%
markup on tokens. Providers bill you directly, at their own list price.
15
auto routing modes, from auto-coding to auto-cheapest.
10 min
between health checks on every provider the router can pick.
Smart Router · live routing decisions
Picks and rankings come from the live router; the requests are examples
Incoming requests
  1. auto-codingstream
    Fix the race condition in checkout.ts
    → GPT-6 Astra · 200 · 9.0 s
Model
auto-coding
Strategy
best_coding
Ranked on
Coding suite: real repository bug fixes, every 4 hours
Passed over
none
Routed to
GPT-6 Astra · 9.0 s
Ranking for this requestCoding score
1GPT-6 AstraOpenAIrouted88
2DeepSeek V4 ProDeepSeekfallback87
3Claude Sonnet 5Anthropicfallback86
4Claude Fable 5.1Anthropic85
5Claude Opus 5.5Anthropic83
6GPT-5.6 SolOpenAI83
7GPT-6.1 SolOpenAI83

Measured and routed across 6 providers

  • OpenAI
  • Anthropic
  • Google
  • DeepSeek
  • Moonshot AI
  • Z.ai
24frontier models scored continuously
144health checks per provider, every day
24canary drift probes per model, every day
6coding runs per model, every day
15routing modes behind one endpoint

Smart Router

One endpoint. Fifteen ways to decide.

Point any OpenAI-compatible client at ASL and choose how each request is routed with the model name. Rankings come from the same scores as the leaderboard and refresh after every benchmark run. Pick a mode to see what it would do right now.

Best quality

Best value

Speed, cost, stability

Adaptive

Best coding

best_coding

The current leader on real repository bug fixes, re-measured every 4 hours.

Ranks on
Coding suite: real repository bug fixes, every 4 hours
Ordered by
Quality (effective score)
Always
Only models you have a key for; drift-flagged models and open circuits go last
If you sent a request nowCoding score
1GPT-6 AstraOpenAIprimary88
2DeepSeek V4 ProDeepSeekfallback87
3Claude Sonnet 5Anthropicfallback86
4Claude Fable 5.1Anthropic85
5Claude Opus 5.5Anthropic83
6GPT-5.6 SolOpenAI83
7GPT-6.1 SolOpenAI83
Primary GPT-6 Astra fallback DeepSeek V4 Pro fallback Claude Sonnet 5
from openai import OpenAI

client = OpenAI(
    base_url="https://aistupidlevel.info/v1",
    api_key="aism_…",  # your ASL router key
)

reply = client.chat.completions.create(
    model="auto-coding",
    messages=[{"role": "user", "content": prompt}],
    stream=True,
)

Response headers

HTTP/1.1 200 OK
X-AISM-Model: gpt-6-astra
X-AISM-Provider: openai
X-AISM-Latency: 8965
X-AISM-Reasoning: Selected gpt-6-astra from openai for best coding performance (7-axis code benchmark) (score: 88.0). Ranked #1 of 24 available models. Last updated 3h ago.

Also speaks Anthropic: native /v1/messages passthrough, plus /v1/embeddings. Works with any client that lets you set a base URL. Router documentation

Router internals

Built for agents in production.

A benchmark-driven pick is only half of a router. These are the details that decide whether it survives real traffic.

0% markup

Your keys, your bill

Requests go out with your own OpenAI, Anthropic, Google, DeepSeek, Moonshot and Z.ai keys, so providers bill you directly. We add nothing to token prices — plans include a number of routed requests.

Per suite

Drift-aware by default

When a model’s detector fires on the suite your strategy depends on — or it has an open canary incident — it drops behind healthy models. The routing reason names who was passed over.

Up to 5 fallbacks

Outages route around you

Your own fallback order of up to 10 models, then automatic picks from other providers. A circuit opens after 5 straight failures and probes again after 60 seconds.

All six providers

Tool loops that don’t derail

Native tool calls with the provider’s own call ids, each model’s reasoning carried between turns, and a loop that stays on the model that started it. Forced tool_choice and json_schema work everywhere — natively, or emulated and checked.

32 MB · 15 min

Long context, long thinking

Native streaming on every provider, request bodies up to 32 MB for 1M-token contexts, and a 15-minute timeout for models that think before they answer.

Per key · per project

Budgets that hold

Hard and soft monthly budgets on every key and project, a maximum price per 1M tokens, a maximum latency, and provider or model exclusions — all checked before a request is sent.

X-AISM-Reasoning

Every pick explained

Each response names the model, the provider, the latency and why it won. Preview any routing setting against the real pipeline without spending a request.

AES-256-GCM

Private by default

Prompt logging is off unless you turn it on. Logged prompts are scrubbed of secrets before they are encrypted, and so are your provider keys.

14-day window

Learns from production

Real failures and your ratings through /v1/router/feedback adjust each model’s effective score, so a model that benchmarks well but fails in practice loses ground.

Benchmarks

Measured around the clock, not once a quarter.

The router is only as good as its data. Every model gets the same tasks, the same harness and the same scoring, on a fixed schedule — shown here in your time zone.

0003060912151821
Your time--:--Next health check in --:--
Provider healthA short completion to every provider with our own key. Failures are re-checked after 15 seconds.
Every 10 min144 a day
Canary drift probeFixed coding probes on every model, compared with its own history using Welch’s t-test.
Hourly24 a day
CodingReal repository bug fixes plus one hard function — 7 tasks, 7 attempts each.
Every 4 hours6 a day
CalibrationKnown unknowns: does a model say so when it can’t know the answer?
Every 6 hours4 a day
Reasoning · tool useMulti-turn engineering sessions checked by code, and sandboxed agent tasks with real tools.
Dailynight run
Robustness · biasPrompt-variation and demographic sweeps, run outside the score.
Dailynight run
Context rotLong-context accuracy from 8K to 1M tokens, by length and position. Pilot.
WeeklyPro and up
How every score is computed

Methodology public. Test tasks private, so no lab can train on them.

On the board

Every model we measure.

24 models from 6 providers. Each has its own page with its score history, drift record and cost — open to everyone.

AI drift detection

When a model quietly changes, you see it — and the router moves on.

Providers ship silent updates. AI Stupid Level compares every model with its own history instead of guessing from one bad run: a Page-Hinkley change-point detector on each suite, plus an hourly canary.

Illustration · an example model’s reasoning score, daily median · last 30 daysscoreown baselinePage-Hinkley

Smart Router · next request

auto-reasoning stops picking the flagged model and routes to the next healthy one. The routing reason names who was passed over, and why.

Flagged models drop behind healthy ones for every strategy that depends on that suite.

Watchlist · email

An email when a model you watch drops 5 points below where it was a week ago. Set your own threshold on paid plans.

Plus a summary every Monday of what moved and what held.

Teams · webhook

A signed callback to your own endpoint when a watched model regresses or a project reaches a budget threshold.

Per suite, per model

Coding, reasoning and tool use each run their own Page-Hinkley detector against the model’s own baseline, tuned on real run-to-run noise.

An hourly canary

Fixed probes run every hour; a sustained shift has to pass Welch’s t-test before it opens an incident.

Evidence, not vibes

Every flag points to the runs behind it. Full history and the diagnosis behind each change come with Pro.

AI drift detection: is your model getting worse?

Provider status

Every provider, checked every 10 minutes.

A short completion goes to each provider with our own key, day and night. Failures are re-checked 15 seconds later and attributed, so the router only avoids real outages — and the status page never blames a vendor for our problem.

All 6 providers answering · last check —Next check in --:--
ProviderNowLatencyLast 7 days, hourlyUptime
OpenAIOperational1.4 s
100%
AnthropicOperational1.2 s
100%
GoogleOperational600 ms
100%
DeepSeekOperational1.0 s
97.91%
Moonshot AIOperational1.1 s
100%
Z.aiOperational1.7 s
100%
OperationalDegradedProvider outageOur side — not counted against the provider
Provider

Unreachable twice while our side is healthy. Opens an incident; the router stops sending traffic.

Our account

A billing or quota answer for our own key. Logged, never shown as the provider’s outage.

Probe

A malformed or timed-out check of our own making. Re-run, not reported.

Our server

Several providers failing together, or our own network down. The router keeps routing.

Open the live status page

Workload assessment

Benchmark the models on your own work.

Public scores tell you which model is best on our tasks. An assessment tells you which one is best on yours — measured by the same harness, the same scoring rules and the same statistics.

  1. 01

    Send up to 20 real tasks

    Prompts, files and the answers you would accept. We confirm the scope within 2 business days.

  2. 02

    We run 3 models of your choice

    In the same sandbox as the public leaderboard, with repeated trials so a lucky run can’t decide the result.

  3. 03

    Report in 7 days

    Per-task results, cost and latency for each model, and our recommendation.

$1,290One-off, paid at booking. Full refund if your tasks can’t be measured. Credited against an annual plan within 30 days.
Book an assessment →

Need it continuously? Custom continuous benchmarking runs your tasks on our schedule, with drift alerts on your own suite. Talk to us.

Data API

Every score, as JSON.

Keyed access to scores, history, drift and incidents — for dashboards, CI gates and model reviews. Build against the free key at 10 requests a day; production tiers go up to 250,000 a day.

GET /api/v1/models/:id/historyasl_ key
curl https://aistupidlevel.info/api/v1/models/292/history?period=7d \
  -H "X-API-Key: $ASL_DATA_KEY"
{
  "success": true,
  "period": "7d",
  "data": {
    "dataPoints": 41,
    "data": [
      { "timestamp": "2026-10-14T10:00:00Z", "score": 86,
        "suite": "combined", "axes": { … } },
      …

Data API documentation

Watchlist & alerts

Know before your users do.

Pick the models you depend on. We tell you when one of them slips — by email, in a weekly summary, or by webhook into your own tools.

  • 3 models free, 20 on Pro and Developer, unlimited on Teams.
  • Email when a watched model falls 5 points below where it was a week ago. Set your own thresholds on paid plans.
  • A weekly summary every Monday of what moved and what held.
  • Signed webhooks for regressions and budget thresholds, and a team watchlist that alerts everyone in the workspace.

Pricing

Start free. Pay when the router earns it.

Free

$0forever

No card required

The public evidence, plus a watchlist of three models with email alerts and a weekly summary.

Create free account

Includes

  • 3 tracked models, with email alerts
  • 7 days of history
  • Every category ranking
  • Smart Router: 1,000 requests a month
  • Data API: 10 requests a day

Pro Intelligence

$120/ year

$10 a month · save $24

Full history, the diagnosis behind every change, calibration and substitute analysis, exports and custom alerts.

Start free trial

Everything in Free, plus

  • 20 tracked models and custom alert thresholds
  • Full history and the drift diagnosis behind every change
  • Calibration and cheaper-substitute analysis
  • Context-rot pilot: long-context accuracy up to 1M tokens
  • Routing analytics and CSV/JSON exports
  • Smart Router: 10,000 requests a month
  • Data API: 10,000 requests a day

Developer

$250/ year

$20.83 a month · save $50

For running the Smart Router in production: ten times the requests, API monitoring and 30-day decision logs.

Start free trial

Everything in Pro, plus

  • Smart Router: 100,000 requests a month
  • API monitoring: per-key logs, costs, prompt auditing and budget limits
  • 30-day decision logs
  • Data API: 25,000 requests a day
  • A workspace with one project and a shared watchlist; viewers free

TeamsMost complete

$1,290/ year

$107.50 a month · save $258

Five editors, each with the full Teams plan, three projects with their own router keys, budgets and spend reports, plus webhooks, single sign-on and an audit trail.

Start free trial

Everything in Developer, plus

  • 5 editors, each with the full Teams plan
  • 3 projects, each with its own router keys, rules, budget and spend report
  • A team watchlist with alerts to everyone
  • Smart Router: 1,000,000 requests a month
  • 90-day decision logs
  • Data API: 100,000 requests a day
  • Webhooks for regressions and budgets
  • Single sign-on (OIDC or SAML), SCIM and an audit trail

EnterpriseContracted scope, unlimited seats and requests, 365-day decision logs and invoicing. 250,000 Data API calls a day.

Talk to us

Past your router allowance? Top up credits from $5 — 2,000 requests per $1, no expiry. Providers bill your tokens directly; we never add to them. Compare every plan

FAQ

Questions people actually ask.

Still unsure? The methodology explains every number on the site, and the full FAQ covers the rest.

Are AI models really getting worse over time?

Sometimes — and usually without notice. Providers change weights, safety layers and serving infrastructure behind the same model name. AI Stupid Level re-runs the same tasks on every model on a fixed schedule and compares each one with its own history, so a drop shows up as data instead of a hunch.

Is ChatGPT getting worse? Is Claude getting worse?

Check the live scores. Every OpenAI and Anthropic model we track is re-tested on coding every 4 hours and on reasoning and tool use every day, and a model is flagged only when a change holds up statistically — not after one bad run.

Which AI model is best for coding right now?

It changes, which is the point. The leaderboard ranks every model we track on real repository bug fixes every 4 hours, and the router’s auto-coding mode sends your request to the current leader among the models you have keys for.

How is the Smart Router different from other LLM routers?

It routes on measured quality, not just price and uptime. Rankings come from our own continuous benchmarks, drift-flagged models drop behind healthy ones, and every response explains its pick in an X-AISM-Reasoning header. You keep your own provider keys and pay providers directly.

Do you mark up tokens or resell inference?

No. Requests are sent with your own provider keys and billed to you by the provider at their list price. Plans include a monthly number of routed requests; past that you can top up credits or move up a plan.

Which providers and models do you cover?

OpenAI, Anthropic, Google, DeepSeek, Moonshot AI (Kimi) and Z.ai (GLM). The router handles text, code and tool calls. It does not route images or audio, because we do not measure them and will not route what we do not measure.

Why do I need an account to see the leaderboard?

A free account costs nothing and includes every category ranking, 7 days of history, a three-model watchlist with email alerts, 1,000 routed requests a month and a Data API key. Model pages, the methodology and the status page stay open to everyone.

Stop guessing which model is best today.

Create a free account to see every ranking, watch three models and route your first 1,000 requests — with your own keys.

Create free account →Log in