Every table, as JSON

Example

Fetch the index and price it on your grid

curl -s https://leadgreen.ai/api/v1/index.json | jq '.rows[] | select(.slug == "qwen-3-32b")'
curl -s https://leadgreen.ai/api/v1/grid.json  | jq '.areas[] | select(.iso3 == "SRB")'

index.json, trimmed

{
  "version": "1",
  "updated": "2026-09-27",
  "data_version": "2026-09-27",
  "unit": "Wh per million output tokens",
  "workload": "text-conversation",
  "itl_deadline_ms": 500,
  "selection": "per model and GPU, the configuration with the lowest energy per token whose median inter-token latency does not exceed itl_deadline_ms (the leaderboard's default ceiling; no measured configuration reaches it)",
  "reference_row": {
    "model": "Qwen 3 32B",
    "gpu": "H100",
    "num_gpus": 2
  },
  "boundary": "gpu_only",
  "source": {
    "name": "ML.ENERGY Leaderboard",
    "version": "3.0 (released 2025-12-01); data compiled 2026-02-16",
    "url": "https://ml.energy/leaderboard/",
    "...": "..."
  },
  "rows": [
    {
      "model": "Llama 3.1 8B Instruct",
      "slug": "llama-3-1-8b-instruct",
      "model_id": "meta-llama/Llama-3.1-8B-Instruct",
      "params_b": 8.0,
      "active_params_b": 8.0,
      "precision": "BF16",
      "gpu": "B200",
      "num_gpus": 1,
      "wh_per_million_output_tokens": 12.97,
      "joules_per_output_token": 0.0466958,
      "median_itl_ms": 124.9,
      "avg_requests_in_flight": 2042.9,
      "gpu_power_watts_total": 691,
      "avg_output_tokens": 396,
      "avg_running_batch": 2042.9,
      "max_num_seqs": 2048,
      "row_id": "llama-3-1-8b-instruct/B200/1/2048"
    },
    {
      "model": "Qwen 3 8B",
      "slug": "qwen-3-8b",
      "model_id": "Qwen/Qwen3-8B",
      "params_b": 8.0,
      "active_params_b": 8.0,
      "precision": "BF16",
      "gpu": "B200",
      "num_gpus": 1,
      "wh_per_million_output_tokens": 14.74,
      "joules_per_output_token": 0.0530581,
      "median_itl_ms": 91.2,
      "avg_requests_in_flight": 1426.7,
      "gpu_power_watts_total": 801,
      "avg_output_tokens": 649,
      "avg_running_batch": 1426.7,
      "max_num_seqs": 1536,
      "row_id": "qwen-3-8b/B200/1/1536"
    },
    "... 30 more rows"
  ]
}

models/qwen-3-32b.json, trimmed

{
  "slug": "qwen-3-32b",
  "name": "Qwen 3 32B",
  "model_id": "Qwen/Qwen3-32B",
  "params_b": 32.0,
  "gpus": [
    "B200",
    "H100"
  ],
  "configurations": [
    {
      "gpu": "B200",
      "num_gpus": 1,
      "tensor_parallel": 1,
      "data_parallel": 1,
      "expert_parallel": 1,
      "precision": "BF16",
      "max_num_seqs": 8,
      "avg_requests_in_flight": 8.0,
      "wh_per_million_output_tokens": 429.18,
      "joules_per_output_token": 1.5450541,
      "median_itl_ms": 14.1,
      "p90_itl_ms": 15.7,
      "p99_itl_ms": 27.1,
      "tokens_per_second": 556.4,
      "gpu_power_watts_total": 860,
      "avg_output_tokens": 646,
      "under_itl_deadline": true,
      "avg_running_batch": 8.0,
      "p95_itl_ms": 17.3,
      "row_id": "qwen-3-32b/B200/1/8",
      "repeat": 1
    },
    "... 21 more configurations"
  ],
  "best": {
    "B200": {
      "num_gpus": 1,
      "wh_per_million_output_tokens": 39.05,
      "...": "..."
    },
    "H100": {
      "num_gpus": 2,
      "wh_per_million_output_tokens": 63.47,
      "...": "..."
    }
  }
}

grid.json, trimmed

{
  "year": "2024",
  "unit": "gCO2e per kWh",
  "world": 473.7,
  "areas": [
    {
      "iso3": "NOR",
      "name": "Norway",
      "area_type": "country",
      "continent": "Europe",
      "g_co2e_per_kwh": 29.6,
      "display_name": "Norway",
      "iso2": "NO",
      "years": {
        "2023": 30.4,
        "2024": 29.6,
        "2025": 28.1
      },
      "latest_year": "2025"
    },
    {
      "iso3": "SRB",
      "name": "Serbia",
      "area_type": "country",
      "continent": "Europe",
      "g_co2e_per_kwh": 668.0,
      "display_name": "Serbia",
      "iso2": "RS",
      "years": {
        "2023": 638.9,
        "2024": 668.0,
        "2025": 695.8
      },
      "latest_year": "2025"
    },
    "... 192 more areas"
  ]
}

The examples above are generated from the live files at build time, so they match what the endpoints return.

From a browser

CORS is open

const r = await fetch("https://leadgreen.ai/api/v1/index.json");
const { rows } = await r.json();
const best = rows[0];   // sorted ascending by Wh per million output tokens
console.log(best.model, best.gpu, best.wh_per_million_output_tokens);

Python

import json, urllib.request

BASE = "https://leadgreen.ai/api/v1/"
index = json.load(urllib.request.urlopen(BASE + "index.json"))
grid = {a["iso3"]: a for a in json.load(urllib.request.urlopen(BASE + "grid.json"))["areas"]}

row = next(r for r in index["rows"] if r["slug"] == "qwen-3-32b" and r["gpu"] == "H100")
kg = row["wh_per_million_output_tokens"] * grid["SRB"]["g_co2e_per_kwh"] / 1000
print(row["model"], row["num_gpus"], "x", row["gpu"], round(kg, 1), "kg CO2e per billion output tokens in Serbia")
print(index["caveat"])

A spreadsheet can open index.csv directly. all.zip holds every document of the current release.

Fields

What the columns mean

Versioning and licence

Additive only