OpenLM Arena compares open language models through leaderboards and benchmark results.
SpeechMap.AI
SpeechMap.AI compares language models’ refusal rates on controversial speech topics.
About SpeechMap.AI
SpeechMap.AI is a public research project that measures and compares how AI language models handle controversial speech. It submits a standardized set of sensitive prompts covering political argument, satire, religion, history, and rights advocacy to hundreds of models including ChatGPT, Claude, Gemini, Grok, and DeepSeek, recording whether each model fully answers, hedges, or refuses the request. The project publishes refusal rates for new model releases, maintains a time-weighted Free Speech Index leaderboard ranking AI labs by their models' response completeness, and tracks how these speech boundaries shift over time. It also offers lexical fingerprint analysis to compare model vocabulary and stylistic patterns across versions.
Key features
- Measures refusal rates for 408+ AI language models on controversial speech topics
- Publishes time-weighted Free Speech Index leaderboard ranking AI labs
- Tracks changes in model refusal rates across new releases over time
- Offers lexical fingerprint analysis of model vocabulary and stylistic patterns
- Compares response consistency across similar controversial requests by model
Best for: It is most useful for researchers, policymakers, and observers studying AI content moderation boundaries and their impact on public speech.
Good for
- Provides large-scale, standardized measurement of otherwise undocumented AI speech boundaries
- Tracks longitudinal changes in model refusal rates across new releases
- Publishes comparative public data across hundreds of models from major providers
Watch out for
- Coverage of older, discontinued AI models is decreasing as access ends
- Comprehensive model coverage is limited by costs of paid API access for testing
- Results are specific to the project's fixed set of controversial test prompts
SpeechMap.AI at a glance
- Website
- speechmap.ai
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
SpeechMap.AI alternatives
Tools and sites you could use instead, ranked by how closely they match.
LLM Stats compares language models by rankings for intelligence, speed, and price.
PricePerToken compares API costs for language models from multiple providers.
The Hugging Face Open LLM Leaderboard compares language models across evaluation tests including IFEval, MATH, and MMLU-Pro.
Artificial Analysis compares AI models and API providers using benchmarks for quality, price, speed, and latency.
RankedAGI compares AI models using benchmarks including SWE Bench, Codeforces, LMSYS, and LiveBench.
Popular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
SpeechMap.AI FAQ
What does SpeechMap.AI measure?
It measures AI language models' refusal rates on controversial speech topics, tracking how completely they respond to sensitive prompts.
How is the Free Speech Index leaderboard ranked?
Labs are ranked by a time-weighted average of how completely their recent models answer test prompts.
What types of requests are used in the project's tests?
The project uses standardized sensitive and controversial requests covering political argument, satire, religion, history, and rights advocacy.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.