{
 "body": "\nPart of the [Arena Elo](arena_elo.md) family.\n\n## What it measures\n\narena_elo_hard_prompts restricts the same anonymous pairwise-vote pool behind the Arena text\nleaderboard to prompts an automatic classifier scored as demanding. LMSYS defined seven hardness\ncriteria \u2014 specificity, domain knowledge, complexity, problem-solving, creativity, technical\naccuracy and real-world application \u2014 and used Llama-3-70B-Instruct to label whether each of over\na million Arena prompts met each one. Prompts meeting six or more of the seven, about 20% of the\nlabelled pool, form the Hard Prompts category, published as separate English and Overall\nleaderboards. A de-duplication step also down-samples very common, low-signal prompts (chiefly\ngreetings) before the leaderboard is built.\n\n## Reading the numbers\n\nA high arena_elo_hard_prompts rating says a model held up on the more demanding slice of real\nuser prompts, not just on the easy majority. The category was built specifically because it\nreorders models relative to the unfiltered board: at launch, Llama-3-8B-Instruct \u2014 rated close to\nGPT-4-0314 on the overall English board \u2014 dropped sharply here, while Claude 3 Opus moved above\nLlama-3-70B-Instruct. Treat a model's Hard-Prompts-versus-Overall gap as a rough signal of how\nmuch of its overall rating rests on easy, low-effort conversations. Style is not controlled in\nthis default view, so check arena_elo_style_control for a length-and-markdown-adjusted ranking of\nthis same category, and check confidence intervals before reading small gaps as meaningful.\n",
 "build": {
  "built_at": "2026-09-09T16:56:50+00:00",
  "commit": "0a599558854c0e238c03a0f0d725239cb28f9d11",
  "eligibility_as_of": "2026-09-09"
 },
 "disposition": {
  "canonical_id": "arena_elo_hard_prompts",
  "reasons": [],
  "status": "unassessed",
  "verified_results": []
 },
 "models_covered": [
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Opus 4.6",
   "model_id": "anthropic/claude-opus-4-6",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1534.7,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, anthropic-system-card-mythos"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5.4",
   "model_id": "openai/gpt-5-4",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1507.2,
   "source": "lmarena.ai, provider-reports, anthropic-system-card-mythos, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 4.20 (Reasoning)",
   "model_id": "xai/grok-4-20-0309-reasoning",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1505.0,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Opus 4.5",
   "model_id": "anthropic/claude-opus-4-5-20251101",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1500.0,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 4.6",
   "model_id": "anthropic/claude-sonnet-4-6",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1498.7,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5.2",
   "model_id": "openai/gpt-5-2",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1495.4,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GLM 5.1",
   "model_id": "zhipu/glm-5-1",
   "provider": "zhipu",
   "provider_display": "Z.ai (Zhipu AI)",
   "score": 1494.3,
   "source": "zai-org-model-card"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 4.20 Multi-Agent",
   "model_id": "xai/grok-4-20-multi-agent-0309",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1491.6,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 4.5",
   "model_id": "anthropic/claude-sonnet-4-5-20250929",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1485.0,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5.4 mini",
   "model_id": "openai/gpt-5-4-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1483.9,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 4",
   "model_id": "xai/grok-4",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1482.8,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5.3 Codex Spark",
   "model_id": "openai/gpt-5-3-codex-spark",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1482.5,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Opus 4.1",
   "model_id": "anthropic/claude-opus-4-1-20250805",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1479.9,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 5",
   "model_id": "zhipu/glm-5",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1475.9,
   "source": null
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5.1",
   "model_id": "openai/gpt-5-1",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1474.6,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemma 4 31B",
   "model_id": "google/gemma-4-31b",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1474.2,
   "source": "lmarena.ai, provider-reports, multimodal-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 4.7",
   "model_id": "zhipu/glm-4-7",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1463.5,
   "source": null
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "gemma 4 26B A4B it",
   "model_id": "google/gemma-4-26b-a4b-it",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1461.1,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.5 Pro",
   "model_id": "google/gemini-2-5-pro",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1460.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o",
   "model_id": "openai/gpt-4o",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1456.0,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Opus 4",
   "model_id": "anthropic/claude-opus-4-20250514",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1455.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5",
   "model_id": "openai/gpt-5",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1447.9,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek V3.2 Exp",
   "model_id": "deepseek/deepseek-v3-2-exp",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 1447.7,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek V3.2",
   "model_id": "deepseek/deepseek-v3-2",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 1446.6,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 4.6",
   "model_id": "zhipu/glm-4-6",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1442.6,
   "source": null
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 4.1 Fast",
   "model_id": "xai/grok-4-1-fast",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1441.8,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 235B-A22B",
   "model_id": "qwen/qwen3-235b-a22b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 1440.4,
   "source": "lmarena.ai, provider-reports, preference-evals, llm-stats, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "o3",
   "model_id": "openai/o3",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1439.7,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Haiku 4.5",
   "model_id": "anthropic/claude-haiku-4-5-20251001",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1436.6,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek R1 0528",
   "model_id": "deepseek/deepseek-r1-0528",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 1433.6,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek V3.1",
   "model_id": "deepseek/deepseek-v3-1",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 1433.3,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 4.5",
   "model_id": "zhipu/glm-4-5",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1432.7,
   "source": null
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 4 Fast (Non-Reasoning)",
   "model_id": "xai/grok-4-fast-non-reasoning",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1432.7,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Large 3",
   "model_id": "mistral/mistral-large-2512",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1431.1,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4.1",
   "model_id": "openai/gpt-4-1",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1430.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, domain-evals preference-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 4",
   "model_id": "anthropic/claude-sonnet-4-20250514",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1430.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Medium 3.1",
   "model_id": "mistral/mistral-medium-2508",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1429.3,
   "source": "lmarena.ai, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 3",
   "model_id": "xai/grok-3",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1426.2,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.5 Flash Preview 09-25",
   "model_id": "google/gemini-2-5-flash-preview-09-2025",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1420.7,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.5 Flash",
   "model_id": "google/gemini-2-5-flash",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1420.0,
   "source": "lmarena.ai, provider-reports, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek R1",
   "model_id": "deepseek/deepseek-r1",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 1418.1,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "o1",
   "model_id": "openai/o1",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1417.4,
   "source": "lmarena.ai, provider-reports, llm-stats, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5.4 nano",
   "model_id": "openai/gpt-5-4-nano",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1417.2,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 3.7",
   "model_id": "anthropic/claude-3-7-sonnet-20250219",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1415.7,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3-Coder 480B-A35B Instruct",
   "model_id": "qwen/qwen3-coder-480b-a35b-instruct",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 1413.6,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek V3 0324",
   "model_id": "deepseek/deepseek-v3-0324",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 1408.3,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "o4-mini",
   "model_id": "openai/o4-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1405.2,
   "source": "lmarena.ai, provider-reports, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4.1 mini",
   "model_id": "openai/gpt-4-1-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1402.3,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5 Mini",
   "model_id": "openai/gpt-5-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1401.8,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Medium 3",
   "model_id": "mistral/mistral-medium-2505",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1401.1,
   "source": "lmarena.ai, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "o3-mini",
   "model_id": "openai/o3-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1401.1,
   "source": "lmarena.ai, provider-reports, llm-stats, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 3.5 v2",
   "model_id": "anthropic/claude-3-5-sonnet-20241022",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1396.7,
   "source": "lmarena.ai, provider-reports, llm-stats, intlpull, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "o1-preview",
   "model_id": "openai/o1-preview",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1396.1,
   "source": "lmarena.ai, provider-reports, llm-stats"
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 4.5 Air",
   "model_id": "zhipu/glm-4-5-air",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1391.2,
   "source": null
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.5 Flash Lite Preview 09-25",
   "model_id": "google/gemini-2-5-flash-lite-preview-09-2025",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1390.7,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 4.7 Flash",
   "model_id": "zhipu/glm-4-7-flash",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1387.9,
   "source": null
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 4.6V",
   "model_id": "zhipu/glm-4-6v",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1384.1,
   "source": null
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.5 Flash Lite",
   "model_id": "google/gemini-2-5-flash-lite",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1380.9,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 3 Mini",
   "model_id": "xai/grok-3-mini",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1377.8,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": null,
   "attribution": "unverified-legacy",
   "display_name": "GLM 4.5V",
   "model_id": "zhipu/glm-4-5v",
   "provider": "zhipu",
   "provider_display": "Zhipu AI",
   "score": 1375.5,
   "source": null
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Small 3.2",
   "model_id": "mistral/mistral-small-2506",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1374.3,
   "source": "lmarena.ai"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Command A",
   "model_id": "cohere/command-a-03-2025",
   "provider": "cohere",
   "provider_display": "Cohere",
   "score": 1367.9,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 32B",
   "model_id": "qwen/qwen3-32b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 1367.6,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemma 3 27B",
   "model_id": "google/gemma-3-27b-it",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1364.9,
   "source": "lmarena.ai, provider-reports, multimodal-evals, open-llm-leaderboard-v2,, domain-evals llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "o1-mini",
   "model_id": "openai/o1-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1360.5,
   "source": "lmarena.ai, provider-reports, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.0 Flash",
   "model_id": "google/gemini-2-0-flash",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1360.4,
   "source": "lmarena.ai, provider-reports, multimodal-evals, llm-stats, intlpull, domain-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 3.5",
   "model_id": "anthropic/claude-3-5-sonnet-20240620",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1358.7,
   "source": "lmarena.ai, provider-reports, llm-stats, intlpull, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-5 Nano",
   "model_id": "openai/gpt-5-nano",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1353.3,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek V3",
   "model_id": "deepseek/deepseek-v3",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 1350.3,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, domain-evals open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 1.5 Pro",
   "model_id": "google/gemini-1-5-pro",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1350.2,
   "source": "lmarena.ai, provider-reports, multimodal-evals, llm-stats, intlpull, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.0 Flash Lite",
   "model_id": "google/gemini-2-0-flash-lite",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1347.9,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen3 30B-A3B",
   "model_id": "qwen/qwen3-30b-a3b",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 1345.6,
   "source": "lmarena.ai, provider-reports, open-llm-leaderboard-v2, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Haiku 3.5",
   "model_id": "anthropic/claude-3-5-haiku-20241022",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1343.3,
   "source": "lmarena.ai, provider-reports, llm-stats, domain-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 3.1 405B Instruct",
   "model_id": "meta/llama-3-1-405b-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 1340.1,
   "source": "lmarena.ai, provider-reports, llm-stats, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 4 Maverick 17B 128E Instruct",
   "model_id": "meta/llama-4-maverick-17b-128e-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 1338.0,
   "source": "lmarena.ai, provider-reports, llm-stats, domain-evals, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o (2024-05-13)",
   "model_id": "openai/gpt-4o-2024-05-13",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1336.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 3.1 405B Instruct FP8",
   "model_id": "meta/llama-3-1-405b-instruct-fp8",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 1334.7,
   "source": "lmarena.ai, provider-reports, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4.1 nano",
   "model_id": "openai/gpt-4-1-nano",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1332.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemma 3 12B",
   "model_id": "google/gemma-3-12b-it",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1331.5,
   "source": "lmarena.ai, provider-reports, open-llm-leaderboard-v2, llm-stats, multimodal-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Magistral Medium (latest)",
   "model_id": "mistral/magistral-medium-latest",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1331.2,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 4 Scout 17B 16E Instruct",
   "model_id": "meta/llama-4-scout-17b-16e-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 1329.0,
   "source": "lmarena.ai, provider-reports, llm-stats, domain-evals, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Opus 3",
   "model_id": "anthropic/claude-3-opus-20240229",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1327.0,
   "source": "lmarena.ai, provider-reports, llm-stats, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o (2024-08-06)",
   "model_id": "openai/gpt-4o-2024-08-06",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1326.3,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Grok 2",
   "model_id": "xai/grok-2",
   "provider": "xai",
   "provider_display": "xAI",
   "score": 1325.7,
   "source": "lmarena.ai, provider-reports, multimodal-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama-3.3-70B-Instruct",
   "model_id": "meta/llama-3-3-70b-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 1320.1,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Small 3.1 24B Instruct 2503",
   "model_id": "mistral/mistral-small-3-1-24b-instruct-2503",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1318.7,
   "source": "lmarena.ai"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen2.5 72B Instruct",
   "model_id": "qwen/qwen2-5-72b-instruct",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 1317.3,
   "source": "lmarena.ai, provider-reports, safety-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4 Turbo",
   "model_id": "openai/gpt-4-turbo",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1315.4,
   "source": "lmarena.ai, provider-reports, llm-stats, intlpull, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Large 2.1",
   "model_id": "mistral/mistral-large-2411",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1312.6,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals,, domain-evals open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o mini",
   "model_id": "openai/gpt-4o-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 1311.1,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 1.5 Flash",
   "model_id": "google/gemini-1-5-flash",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1302.4,
   "source": "lmarena.ai, provider-reports, llm-stats, intlpull, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 3.1 70B Instruct",
   "model_id": "meta/llama-3-1-70b-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 1297.6,
   "source": "lmarena.ai, provider-reports, safety-evals, domain-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Small 24B Instruct 2501",
   "model_id": "mistral/mistral-small-24b-instruct-2501",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 1284.3,
   "source": "lmarena.ai"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemma 3 4B",
   "model_id": "google/gemma-3-4b-it",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1283.4,
   "source": "lmarena.ai, provider-reports, llm-stats, multimodal-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "gemma 2 27B it",
   "model_id": "google/gemma-2-27b-it",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1280.9,
   "source": "lmarena.ai, provider-reports, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 3",
   "model_id": "anthropic/claude-3-sonnet-20240229",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1280.5,
   "source": "lmarena.ai, provider-reports, llm-stats, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "phi 4",
   "model_id": "microsoft/phi-4",
   "provider": "microsoft",
   "provider_display": "Microsoft",
   "score": 1277.2,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2,, domain-evals llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Haiku 3",
   "model_id": "anthropic/claude-3-haiku-20240307",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 1263.2,
   "source": "lmarena.ai, provider-reports, llm-stats, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Command R+",
   "model_id": "cohere/command-r-plus-08-2024",
   "provider": "cohere",
   "provider_display": "Cohere",
   "score": 1259.3,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 1.5 Flash-8B",
   "model_id": "google/gemini-1-5-flash-8b",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1258.2,
   "source": "lmarena.ai, provider-reports, llm-stats, intlpull, multimodal-evals, safety-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "gemma 2 9B it",
   "model_id": "google/gemma-2-9b-it",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 1256.0,
   "source": "lmarena.ai, provider-reports, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Command R",
   "model_id": "cohere/command-r-08-2024",
   "provider": "cohere",
   "provider_display": "Cohere",
   "score": 1254.6,
   "source": "lmarena.ai, provider-reports, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 3.1 8B Instruct",
   "model_id": "meta/llama-3-1-8b-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 1221.8,
   "source": "lmarena.ai, provider-reports, safety-evals, open-llm-leaderboard-v2"
  }
 ],
 "page": {
  "aliases": [
   "Chatbot Arena Hard Prompts",
   "LMArena Hard Prompts category"
  ],
  "category": "human-preference",
  "contamination": {
   "note": "Same as the arena_elo family: prompts are live user submissions, not a fixed, publishable answer key.",
   "risk": "low"
  },
  "dataset": {
   "languages": [],
   "license": "",
   "modalities": [
    "text"
   ],
   "public_test_set": null,
   "size": null,
   "size_note": "Built from a pool of over 1 million labelled Arena prompts (as of the May 2024 launch post); prompts meeting 6 or more of 7 hardness criteria, about 20% of that pool, qualify for the category.",
   "splits": "Published as two leaderboards: Hard Prompts (English) and Hard Prompts (Overall, multilingual).",
   "url": "https://huggingface.co/lmarena-ai"
  },
  "freshness": {
   "researched": "2026-09-08",
   "researched_by": "sonnet-5 agent, batch 1b, slice J",
   "reviewed": "",
   "reviewed_by": ""
  },
  "harness": {
   "bigbench": "",
   "helm": "",
   "inspect_evals": "",
   "lm_eval": "",
   "opencompass": "",
   "other": "No offline harness; ratings come only from live votes on the platform's Text arena, filtered to this category. The underlying hardness classifier and de-duplication script are open-sourced in the lm-sys/FastChat repository."
  },
  "id": "arena_elo_hard_prompts",
  "last_updated": "",
  "leaderboard_url": "https://arena.ai/leaderboard/text",
  "lineage": {
   "family": "arena_elo",
   "predecessor": "",
   "successors": [],
   "variants": []
  },
  "measures": "arena_elo_hard_prompts restricts the same anonymous pairwise-vote pool behind the Arena text leaderboard to prompts an automatic classifier scored as demanding. LMSYS defined seven hardness criteria \u2014 specificity, domain knowledge, complexity, problem-solving, creativity, technical accuracy and real-world application \u2014 and used Llama-3-70B-Instruct to label whether each of over a million Arena prompts met each criterion. Prompts meeting six or more of the seven (about 20% of the labelled pool) form the Hard Prompts category, published as separate English and Overall (multilingual) leaderboards. A de-duplication step also down-samples very common, low-signal prompts (chiefly greetings) before the leaderboard is built.\n",
  "metric": {
   "baseline_note": "Same anchored, open-ended scale as the arena_elo family: no fixed random baseline or maximum.",
   "direction": "higher_is_better",
   "human_baseline": null,
   "max_score": null,
   "name": "Elo",
   "random_baseline": null,
   "unit": ""
  },
  "name": "Arena Elo \u2014 Hard Prompts",
  "page_kind": "subset",
  "paper": {
   "arxiv": "2403.04132",
   "title": "Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference",
   "url": "https://arxiv.org/abs/2403.04132",
   "year": 2024
  },
  "publisher": {
   "authors": [
    "Tianle Li",
    "Wei-Lin Chiang",
    "Lisa Dunlap"
   ],
   "org": "LMSYS (Large Model Systems Organization), UC Berkeley Sky Computing Lab (founding org); operates today as Arena (formerly LMArena)",
   "url": "https://arena.ai"
  },
  "released": "2024-05",
  "repo_url": "https://github.com/lm-sys/FastChat",
  "saturation": {
   "as_of": "",
   "note": "No current score snapshot for this category specifically was captured from a source read for this page; see arena_elo_overall for the current state of the unfiltered text leaderboard.",
   "status": "unknown",
   "top_score": null
  },
  "sources": [
   {
    "accessed": "2026-09-08",
    "title": "Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference (arXiv)",
    "url": "https://arxiv.org/abs/2403.04132"
   },
   {
    "accessed": "2026-09-08",
    "title": "Introducing Hard Prompts Category in Chatbot Arena (LMSYS blog)",
    "url": "https://www.lmsys.org/blog/2024-05-17-category-hard"
   },
   {
    "accessed": "2026-09-08",
    "title": "Text Arena leaderboard (Arena)",
    "url": "https://arena.ai/leaderboard/text"
   }
  ],
  "status": "active",
  "subcategory": "pairwise human preference, algorithmically hard prompts",
  "summary": "An Arena leaderboard built only from votes on prompts an automatic classifier scored as complex and demanding across several hardness criteria.",
  "tags": [
   "human-preference",
   "chatbot",
   "elo",
   "hard-prompts"
  ],
  "task_format": "Anonymous, randomized side-by-side text chat restricted to prompts scoring 6 or more of 7 hardness criteria; a user votes for the preferred response."
 }
}