{
  "claim": "TypeSafe's homepage headline is 'up to 193.6x faster, up to 444.6x cheaper.' The xArm7 repository is the only place in this ecosystem that publishes a matched, independently replayable head-to-head with per-call costs and per-call model wait times for both sides. Read against it, the cost multiplier is roughly the right order of magnitude and the speed multiplier is not: the measured per-call latency ratio is 4.57x, about 42 times smaller than the headline.",
  "method": "Every figure in the 'measured' rows is read directly from verification/gpt6-comparison.json in openroboto-ai/jev-robot-control, pair 20260919-200239-715974-0, and divided. cost_usd and model_wait_seconds are per-run totals; api_calls is the per-run count of model requests. Per-call figures are total divided by api_calls. The repo's own offline verifier re-executes every recorded motor command in MuJoCo and reports max_qpos_error = 0.0 and cost_sum_verified = true for both arms. The last two rows invert the headline multiplier: they are the per-call LLM latency that would be required to reach 193.6x against Jev's measured latency in each of the two published harnesses.",
  "source": "openroboto-ai/jev-robot-control verification/gpt6-comparison.json and docs/RESULTS.md; browser-use/jev-ultrafast docs/performance.md; TypeSafe homepage figure as itemized in this site's earlier Jev piece.",
  "captured": "2026-09-19",
  "note": "This is ONE seed-0 trial per controller, which the repository states plainly and which is the reason it is evidence about magnitudes rather than a success rate. Both sides are remote HTTP endpoints over OpenRouter, so both latencies include a network round trip; that inflates Jev's absolute number and therefore makes the 4.57x ratio a conservative floor for Jev, not a ceiling. GPT-6 Astra ran at low reasoning effort with 4,096 max completion tokens — a long-reasoning-trace configuration would move the latency ratio up and is the only regime in which a three-figure speed multiplier is reachable.",
  "columns": [
    { "key": "quantity", "label": "quantity" },
    { "key": "jev", "label": "Jev 1.13", "align": "right" },
    { "key": "llm", "label": "GPT-6 Astra (low)", "align": "right" },
    { "key": "ratio", "label": "ratio", "align": "right" },
    { "key": "kind", "label": "" }
  ],
  "rows": [
    { "quantity": "model API calls", "jev": "226", "llm": "212", "ratio": "0.94x", "kind": "measured" },
    { "quantity": "total model cost", "jev": "$0.018825", "llm": "$5.933624", "ratio": "315.2x", "kind": "measured" },
    { "quantity": "cost per call", "jev": "$0.0000833", "llm": "$0.027989", "ratio": "336.0x", "kind": "measured" },
    { "quantity": "total model wait", "jev": "159.81 s", "llm": "685.75 s", "ratio": "4.29x", "kind": "measured" },
    { "quantity": "latency per call", "jev": "0.7071 s", "llm": "3.2347 s", "ratio": "4.57x", "kind": "measured" },
    { "quantity": "wall time, whole task", "jev": "181.85 s", "llm": "707.27 s", "ratio": "3.89x", "kind": "measured" },
    { "quantity": "control cycles to place the apple", "jev": "113", "llm": "106", "ratio": "0.94x", "kind": "measured" },
    { "quantity": "headline cost multiplier", "jev": "—", "llm": "—", "ratio": "444.6x", "kind": "claimed" },
    { "quantity": "headline speed multiplier", "jev": "—", "llm": "—", "ratio": "193.6x", "kind": "claimed" },
    { "quantity": "LLM latency 193.6x would require (vs Jev at 0.707 s, xArm7)", "jev": "0.7071 s", "llm": "136.9 s", "ratio": "193.6x", "kind": "implied" },
    { "quantity": "LLM latency 193.6x would require (vs Jev at 178 ms, browser)", "jev": "0.178 s", "llm": "34.5 s", "ratio": "193.6x", "kind": "implied" }
  ]
}