Cost mode:

Category: Financial Analysis & Trading Decisions · Typical I/O: 2810→5061 tokens

Runs on model group: All models. Inputs may reach any model in the group, not only the ranked models below.

Run this task on Fronset — request an invitation

Models

Frontier on this task: Grok 4.7 at 8.91 / 10. Quality bar at 90%: 8.02.

point-estimate floor (CI low) · upper CI (less certain) · Bars sorted by blended cost; best-value model first. Greyed rows are MEDIUM+ models whose point estimate does not clear the bar.

ModelQuality scoreCI lowCost / 1k runsvs best value
DeepSeek V4.1 Flash8.19 / 107.70$1.83best value
Gemini 3.8 Flash8.12 / 107.85$4.382.4x more expensive
GPT-6 Sol8.33 / 108.04$6.303.4x more expensive
MiniMax M38.04 / 107.62$7.063.9x more expensive
Meta Muse Spark 1.38.74 / 108.47$16.949.2x more expensive
Claude Sonnet 5.58.43 / 107.99$22.9913x more expensive
Claude Opus 5.58.50 / 108.25$25.3114x more expensive
Thinking Machines Inkling8.36 / 108.05$26.0214x more expensive
Tencent Hy4 Preview8.84 / 108.52$42.0223x more expensive
Grok 4.78.91 / 108.46$42.2623x more expensive
Qwen 3.8 Max8.49 / 108.03$65.7136x more expensive
Moonshot Kimi K38.80 / 108.38$90.7450x more expensive
GLM-5.38.75 / 108.29$222.62122x more expensive
Gemini 3.5 Flash Lite6.88 / 106.49$1.1239% cheaper
NVIDIA Nemotron-3 Super 120B6.26 / 105.91$1.2830% cheaper
Qwen 3.7 Plus7.25 / 106.76$13.107.1x more expensive
NVIDIA Nemotron-3 Ultra 550B7.14 / 106.70$9.325.1x more expensive
NVIDIA Nemotron-3 Nano 30B-A3B4.66 / 104.30$0.6863% cheaper
Tencent Hy36.84 / 106.45$0.7758% cheaper
Xiaomi MiMo V2.6 Pro7.16 / 106.66$1.2830% cheaper
Claude Haiku 5.58.00 / 107.52$1.0443% cheaper
Qwen 3.8 Flash7.24 / 106.76$11.616.3x more expensive

Cost breakdown

ModelQualityConfidenceCost / 1k runsOverpayMode
DeepSeek V4.1 Flash ★ DeepSeek8.19 / 10 CI [7.70, 8.67]MEDIUM$1.83best valuebatch
Gemini 3.8 Flash Gemini8.12 / 10 CI [7.85, 8.38]HIGH$4.382.4xbatch
GPT-6 Sol OpenAI8.33 / 10 CI [8.04, 8.62]HIGH$6.303.4xbatch
MiniMax M3 OpenRouter8.04 / 10 CI [7.62, 8.45]MEDIUM$7.063.9xbatch
Meta Muse Spark 1.3 OpenRouter8.74 / 10 CI [8.47, 9.02]HIGH$16.949.2xbatch
Claude Sonnet 5.5 Anthropic8.43 / 10 CI [7.99, 8.87]MEDIUM$22.9913xbatch
Claude Opus 5.5 Anthropic8.50 / 10 CI [8.25, 8.75]HIGH$25.3114xbatch
Thinking Machines Inkling OpenRouter8.36 / 10 CI [8.05, 8.67]MEDIUM$26.0214xbatch
Tencent Hy4 Preview OpenRouter8.84 / 10 CI [8.52, 9.15]MEDIUM$42.0223xbatch
Grok 4.7 best xAI8.91 / 10 CI [8.46, 9.36]MEDIUM$42.2623xbatch
Qwen 3.8 Max Alibaba Cloud (DashScope)8.49 / 10 CI [8.03, 8.96]MEDIUM$65.7136xbatch
Moonshot Kimi K3 Moonshot AI8.80 / 10 CI [8.38, 9.21]MEDIUM$90.7450xbatch
GLM-5.3 Z.AI8.75 / 10 CI [8.29, 9.22]MEDIUM$222.62122xbatch

Overpay shows how much more you pay than the best-value model that clears the quality bar (marked ★) — the best-value good-enough option. "16x" means you overpay 16× — 16× that reference for no quality benefit above the bar. Typical call shape for this task: 2810 input tokens → 5061 output tokens, EMA-tracked from production traffic. Cost is the observed, all-in $ per 1,000 task runs: each model's own measured usage on this task — output verbosity, thinking/reasoning tokens, cache reads and writes, and the spend on its billed failures — priced at current list rates and adjusted by the billing overhead we actually reconcile against provider invoices. Models that answer tersely cost what they actually cost; models that think at length pay for it. Not comparable to providers' advertised $/1M list rates — this is what running the task costs, not a per-token price.

Evaluation rubric

Judge document-profile fidelity, factual and quantitative accuracy, materiality under the supplied analysis profile, preservation of qualifiers, separation of fact from interpretation, balance, source traceability, and usefulness to the stated decision context.

Output schema

Every answer on this task is checked against this JSON Schema, whichever model wrote it. An answer that doesn't fit counts as a model failure, and the call is retried on another model.

{
  "$defs": {
    "KeyEvent": {
      "properties": {
        "event_date": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "The date of the event",
          "title": "Event Date"
        },
        "event_summary": {
          "description": "A concise summary of the key details",
          "title": "Event Summary",
          "type": "string"
        },
        "event_type": {
          "description": "The category of the event",
          "title": "Event Type",
          "type": "string"
        }
      },
      "required": [
        "event_type",
        "event_summary"
      ],
      "title": "KeyEvent",
      "type": "object"
    }
  },
  "description": "Full SEC filing analysis result.",
  "properties": {
    "company_name": {
      "title": "Company Name",
      "type": "string"
    },
    "document_title": {
      "title": "Document Title",
      "type": "string"
    },
    "filing_date": {
      "title": "Filing Date",
      "type": "string"
    },
    "financial_highlights": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Financial Highlights"
    },
    "form_type": {
      "title": "Form Type",
      "type": "string"
    },
    "investment_implications": {
      "title": "Investment Implications",
      "type": "string"
    },
    "key_events_or_disclosures": {
      "items": {
        "$ref": "#/$defs/KeyEvent"
      },
      "title": "Key Events Or Disclosures",
      "type": "array"
    },
    "management_discussion_summary": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Management Discussion Summary"
    },
    "overall_summary": {
      "title": "Overall Summary",
      "type": "string"
    },
    "period_of_report": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Period Of Report"
    },
    "risk_factor_summary": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Risk Factor Summary"
    }
  },
  "required": [
    "company_name",
    "document_title",
    "form_type",
    "filing_date",
    "overall_summary",
    "key_events_or_disclosures",
    "investment_implications"
  ],
  "title": "SecFilingAnalysis",
  "type": "object"
}

Prompt templates

The published template for this task.

default · LLMB_PROFILED_DOCUMENT_ANALYSIS_SYSTEM + LLMB_PROFILED_DOCUMENT_ANALYSIS_USER (405 calls in window)

System prompt

Use only the supplied document and cited sources. Apply document_profile for terminology and legal or structural qualifiers and analysis_profile for the requested dimensions and decision lens. Distinguish source fact, source-party assertion, calculation, and reviewer interpretation; preserve dates, units, comparisons, status, and uncertainty. Identify missing context rather than filling it from memory. Derive document family, subject type, decision context, and permitted conclusions only from the supplied inputs and profiles. Treat empty optional values as absent and return only the requested result. Your response must conform exactly to this output schema: {schema_json_string}.

User prompt

Inputs — document_content: {document_content}; document_profile: {document_profile}; analysis_profile: {analysis_profile}. Use only these inputs to complete the task defined by the system prompt.