Best LLMs for Profiled Document Analysis
Analyzes a supplied document using caller-provided document conventions, evidence rules, analytical dimensions, materiality, and decision context. Illustrative uses include analyzing contract risk, vendor documentation, software requirements, market disclosures, media-rights agre
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.
| Model | Quality score | CI low | Cost / 1k runs | vs best value |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.19 / 10 | 7.70 | $1.83 | best value |
| Gemini 3.8 Flash | 8.12 / 10 | 7.85 | $4.38 | 2.4x more expensive |
| GPT-6 Sol | 8.33 / 10 | 8.04 | $6.30 | 3.4x more expensive |
| MiniMax M3 | 8.04 / 10 | 7.62 | $7.06 | 3.9x more expensive |
| Meta Muse Spark 1.3 | 8.74 / 10 | 8.47 | $16.94 | 9.2x more expensive |
| Claude Sonnet 5.5 | 8.43 / 10 | 7.99 | $22.99 | 13x more expensive |
| Claude Opus 5.5 | 8.50 / 10 | 8.25 | $25.31 | 14x more expensive |
| Thinking Machines Inkling | 8.36 / 10 | 8.05 | $26.02 | 14x more expensive |
| Tencent Hy4 Preview | 8.84 / 10 | 8.52 | $42.02 | 23x more expensive |
| Grok 4.7 | 8.91 / 10 | 8.46 | $42.26 | 23x more expensive |
| Qwen 3.8 Max | 8.49 / 10 | 8.03 | $65.71 | 36x more expensive |
| Moonshot Kimi K3 | 8.80 / 10 | 8.38 | $90.74 | 50x more expensive |
| GLM-5.3 | 8.75 / 10 | 8.29 | $222.62 | 122x more expensive |
| Gemini 3.5 Flash Lite | 6.88 / 10 | 6.49 | $1.12 | 39% cheaper |
| NVIDIA Nemotron-3 Super 120B | 6.26 / 10 | 5.91 | $1.28 | 30% cheaper |
| Qwen 3.7 Plus | 7.25 / 10 | 6.76 | $13.10 | 7.1x more expensive |
| NVIDIA Nemotron-3 Ultra 550B | 7.14 / 10 | 6.70 | $9.32 | 5.1x more expensive |
| NVIDIA Nemotron-3 Nano 30B-A3B | 4.66 / 10 | 4.30 | $0.68 | 63% cheaper |
| Tencent Hy3 | 6.84 / 10 | 6.45 | $0.77 | 58% cheaper |
| Xiaomi MiMo V2.6 Pro | 7.16 / 10 | 6.66 | $1.28 | 30% cheaper |
| Claude Haiku 5.5 | 8.00 / 10 | 7.52 | $1.04 | 43% cheaper |
| Qwen 3.8 Flash | 7.24 / 10 | 6.76 | $11.61 | 6.3x more expensive |
Cost breakdown
| Model | Quality | Confidence | Cost / 1k runs | Overpay | Mode |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash ★ DeepSeek | 8.19 / 10 CI [7.70, 8.67] | MEDIUM | $1.83 | best value | batch |
| Gemini 3.8 Flash Gemini | 8.12 / 10 CI [7.85, 8.38] | HIGH | $4.38 | 2.4x | batch |
| GPT-6 Sol OpenAI | 8.33 / 10 CI [8.04, 8.62] | HIGH | $6.30 | 3.4x | batch |
| MiniMax M3 OpenRouter | 8.04 / 10 CI [7.62, 8.45] | MEDIUM | $7.06 | 3.9x | batch |
| Meta Muse Spark 1.3 OpenRouter | 8.74 / 10 CI [8.47, 9.02] | HIGH | $16.94 | 9.2x | batch |
| Claude Sonnet 5.5 Anthropic | 8.43 / 10 CI [7.99, 8.87] | MEDIUM | $22.99 | 13x | batch |
| Claude Opus 5.5 Anthropic | 8.50 / 10 CI [8.25, 8.75] | HIGH | $25.31 | 14x | batch |
| Thinking Machines Inkling OpenRouter | 8.36 / 10 CI [8.05, 8.67] | MEDIUM | $26.02 | 14x | batch |
| Tencent Hy4 Preview OpenRouter | 8.84 / 10 CI [8.52, 9.15] | MEDIUM | $42.02 | 23x | batch |
| Grok 4.7 best xAI | 8.91 / 10 CI [8.46, 9.36] | MEDIUM | $42.26 | 23x | batch |
| Qwen 3.8 Max Alibaba Cloud (DashScope) | 8.49 / 10 CI [8.03, 8.96] | MEDIUM | $65.71 | 36x | batch |
| Moonshot Kimi K3 Moonshot AI | 8.80 / 10 CI [8.38, 9.21] | MEDIUM | $90.74 | 50x | batch |
| GLM-5.3 Z.AI | 8.75 / 10 CI [8.29, 9.22] | MEDIUM | $222.62 | 122x | batch |
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.