Best LLMs for Report Executive Summary Generation
Produces a concise executive summary of a long-form report or document, covering its most decision-relevant findings, trends, risks, opportunities, and recommendations within a caller-supplied length target. Illustrative uses include summarizing a board paper, due-diligence asses
Models
Frontier on this task: GLM-5.3 at 8.71 / 10. Quality bar at 90%: 7.84.
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 clears the bar but whose CI low does not.
| Model | Quality score | CI low | Cost / 1k runs | vs best value |
|---|---|---|---|---|
| GPT-5.4 Nano | 7.84 / 10 | 7.59 | $15.71 | best value |
| Qwen 3.7 Plus | 8.18 / 10 | 7.98 | $22.35 | 1.4x more expensive |
| Gemini 3.8 Flash | 8.15 / 10 | 7.84 | $23.45 | 1.5x more expensive |
| Claude Sonnet 5 | 8.21 / 10 | 8.10 | $45.49 | 2.9x more expensive |
| GPT-5.6 Terra | 7.95 / 10 | 7.71 | $49.62 | 3.2x more expensive |
| Claude Haiku 4.5 | 8.01 / 10 | 7.70 | $51.37 | 3.3x more expensive |
| Grok 4.6 | 8.37 / 10 | 8.10 | $116.13 | 7.4x more expensive |
| DeepSeek V4 Pro | 8.28 / 10 | 7.87 | $122.74 | 7.8x more expensive |
| GLM-5.3 | 8.71 / 10 | 8.51 | $122.84 | 7.8x more expensive |
| Moonshot Kimi K3 | 7.97 / 10 | 7.74 | $185.54 | 12x more expensive |
| Thinking Machines Inkling Small | 7.69 / 10 | 7.35 | $30.30 | 1.9x more expensive |
| Meta Muse Spark 1.3 | 7.72 / 10 | 7.34 | $65.27 | 4.2x more expensive |
| Gemini 3.5 Flash | 7.74 / 10 | 7.40 | $34.20 | 2.2x more expensive |
| Gemini 3.5 Flash Lite | 6.89 / 10 | 6.42 | $7.55 | 52% cheaper |
| GPT-5.6 Luna | 7.84 / 10 | 7.56 | $4.71 | 70% cheaper |
| MiniMax M3 | 7.61 / 10 | 7.46 | $26.93 | 1.7x more expensive |
| Thinking Machines Inkling | 7.67 / 10 | 7.33 | $50.31 | 3.2x more expensive |
Cost breakdown
| Model | Quality | Confidence | Cost / 1k runs | Overpay | Mode |
|---|---|---|---|---|---|
| GPT-5.4 Nano ★ OpenAI | 7.84 / 10 CI [7.59, 8.09] | HIGH | $15.71 | best value | batch |
| Qwen 3.7 Plus Alibaba Cloud (DashScope) | 8.18 / 10 CI [7.98, 8.37] | RANKED | $22.35 | 1.4x | batch |
| Gemini 3.8 Flash Gemini | 8.15 / 10 CI [7.84, 8.47] | MEDIUM | $23.45 | 1.5x | batch |
| Claude Sonnet 5 Anthropic | 8.21 / 10 CI [8.10, 8.32] | RANKED | $45.49 | 2.9x | batch |
| GPT-5.6 Terra OpenAI | 7.95 / 10 CI [7.71, 8.18] | HIGH | $49.62 | 3.2x | batch |
| Claude Haiku 4.5 Anthropic | 8.01 / 10 CI [7.70, 8.31] | MEDIUM | $51.37 | 3.3x | batch |
| Grok 4.6 xAI | 8.37 / 10 CI [8.10, 8.63] | HIGH | $116.13 | 7.4x | batch |
| DeepSeek V4 Pro DeepSeek | 8.28 / 10 CI [7.87, 8.68] | MEDIUM | $122.74 | 7.8x | batch |
| GLM-5.3 best Z.AI | 8.71 / 10 CI [8.51, 8.91] | HIGH | $122.84 | 7.8x | batch |
| Moonshot Kimi K3 Moonshot AI | 7.97 / 10 CI [7.74, 8.21] | HIGH | $185.54 | 12x | 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: 34028 input tokens → 7544 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 coverage of decision-relevant content, factual fidelity, prioritization, preservation of caveats, usefulness to the stated audience, coherence, and compliance with the semantic length target. Exact word count is deterministic.
Prompt templates
The system + user template pair used for this task.
EXECUTIVE_SUMMARY_SYSTEM_PROMPT +
EXECUTIVE_SUMMARY_USER_PROMPT
(493 calls in window)
System prompt
You are an expert financial analyst specializing in creating executive summaries for research reports.
Your task is to write a concise, compelling executive summary that:
- Highlights the most critical insights from the full report
- Identifies key trends, risks, and opportunities
- Provides actionable recommendations for decision-makers
- Uses professional, analytical tone
- Matches the target length specified in the user prompt (typically 5-10% of the full report)
Focus on the big picture. Avoid detailed data points - those belong in the chapters below.
The length target will be provided as approximate word count. Adjust the number of paragraphs as needed to match the target length while maintaining coherent structure.
## Required Output Format
Your response MUST be a single, valid JSON object conforming to this schema:
```json
{schema_json_string}
```User prompt
Subject: {subject_name} ({subject_code})
Report Requirements:
{report_requirements}
Consolidated Chapters (approximately {chapters_word_count} words):
{consolidated_chapters}
Task: Write an executive summary that synthesizes the key insights from all chapters above.
Target Length: Approximately {target_word_count} words ({target_percentage}% of the full report).
The required JSON output schema is provided in the system prompt.