{
  "site": {
    "name": "Openbenchmarks for Agents",
    "url": "https://openbenchmarks.com",
    "description": "Open benchmarks for Agents - verified benchmarks for build vs buy decisions on AI agent tooling."
  },
  "last_updated": "2026-08-07T13:00:00.000Z",
  "benchmarks": [
    {
      "slug": "lookalikes",
      "name": "Lookalike Benchmark",
      "description": "Head-to-head benchmark for company lookalike APIs (Ocean.io, Exa, Parallel, PredictLeads). Each vendor returns its top-K lookalikes per seed company; an LLM judge scores every returned company for relevance. Cell value = Precision@K, headline metric = avg Precision@K across the seed cohort.",
      "page_url": "https://openbenchmarks.com/lookalikes",
      "api_url": "https://openbenchmarks.com/api/benchmarks/lookalikes",
      "source_repo": "https://github.com/openbenchmarks-labs/lookalikes",
      "status": "live",
      "provider_count": 7,
      "canonical_categories": [
        "b2b-saas",
        "devtools",
        "ecommerce",
        "healthtech",
        "home-services",
        "trades",
        "real-estate",
        "fintech",
        "cybersecurity",
        "industrial",
        "logistics",
        "hospitality",
        "energy"
      ],
      "winners": {
        "highest_avg_precision_at_k": {
          "provider": "Parallel",
          "avg_precision_at_k": 67.54,
          "seeds_judged": 48,
          "k": 100
        }
      }
    },
    {
      "slug": "voice-agent-latency",
      "name": "Voice Agent Latency Benchmark",
      "description": "First-party benchmark measuring Time To First Audio Byte (TTFAB) of voice AI agent platforms over real phone calls, from saved call audio — never from platform-reported timestamps. Includes a per-turn latency curve (does the agent slow down as the conversation grows?).",
      "page_url": "https://openbenchmarks.com/voice-agent-latency",
      "api_url": "https://openbenchmarks.com/api/benchmarks/voice-agent-latency",
      "status": "live",
      "provider_count": 5,
      "winners": {
        "lowest_median_ttfab": {
          "provider": "Telnyx",
          "ttfab_onset_p50_ms": 1296,
          "turns_usable": 419,
          "is_comparison": true
        }
      }
    },
    {
      "slug": "text-to-speech-benchmark-by-coval",
      "name": "Text-to-Speech Benchmark (by Coval)",
      "description": "Independent text-to-speech benchmark by Coval: Time to First Audio (TTFA) latency and Word Error Rate across providers, measured under production-realistic conditions. Coval is a voice-AI evaluation platform (not a model vendor); results mirrored here with attribution and reproducible from Coval's open-source runner.",
      "page_url": "https://openbenchmarks.com/text-to-speech-benchmark-by-coval",
      "data_url": "https://raw.githubusercontent.com/openbenchmarks-labs/tts-stt-benchmarks-by-coval/main/coval-benchmarks.json",
      "attribution": "Coval",
      "source_url": "https://benchmarks.coval.ai",
      "source_repo": "https://github.com/openbenchmarks-labs/tts-stt-benchmarks-by-coval",
      "methodology_url": "https://github.com/coval-ai/benchmarks",
      "status": "live",
      "provider_count": 19,
      "last_synced": "2026-08-07T07:01:36.958Z",
      "winners": {
        "lowest_median_latency": {
          "provider": "palabra",
          "model": "palabra-tts-v1",
          "metric": "TTFA",
          "median_ms": 104.74585650008794
        },
        "lowest_word_error_rate": {
          "provider": "fishaudio",
          "model": "s1",
          "wer_percent": 0
        }
      }
    },
    {
      "slug": "speech-to-text-benchmark-by-coval",
      "name": "Speech-to-Text Benchmark (by Coval)",
      "description": "Independent speech-to-text benchmark by Coval: Time to Final Segment (TTFS) latency and Word Error Rate across providers, measured under production-realistic conditions. Coval is a voice-AI evaluation platform (not a model vendor); results mirrored here with attribution and reproducible from Coval's open-source runner.",
      "page_url": "https://openbenchmarks.com/speech-to-text-benchmark-by-coval",
      "data_url": "https://raw.githubusercontent.com/openbenchmarks-labs/tts-stt-benchmarks-by-coval/main/coval-benchmarks.json",
      "attribution": "Coval",
      "source_url": "https://benchmarks.coval.ai",
      "source_repo": "https://github.com/openbenchmarks-labs/tts-stt-benchmarks-by-coval",
      "methodology_url": "https://github.com/coval-ai/benchmarks",
      "status": "live",
      "provider_count": 17,
      "last_synced": "2026-08-07T07:01:36.958Z",
      "winners": {
        "lowest_median_latency": {
          "provider": "together",
          "model": "parakeet-tdt-0.6b-v3",
          "metric": "TTFS",
          "median_ms": 59.800097004277575
        },
        "lowest_word_error_rate": {
          "provider": "assemblyai",
          "model": "universal-3.5-pro",
          "wer_percent": 3.0649647704928245
        }
      }
    }
  ],
  "docs": {
    "openapi": "https://openbenchmarks.com/openapi.json",
    "llms": "https://openbenchmarks.com/llms.txt",
    "methodology": "https://openbenchmarks.com/lookalikes#methodology"
  }
}