Cost mode:

Category: Topic Organization & Clustering · Typical I/O: 3272→6873 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: GLM-5.3 at 8.88 / 10. Quality bar at 90%: 7.99.

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
Xiaomi MiMo V2.6 Flash8.17 / 107.91$0.24best value
Tencent Hy38.24 / 107.96$0.773.2x more expensive
Xiaomi MiMo V2.6 Pro8.51 / 108.25$1.104.5x more expensive
NVIDIA Nemotron-3 Ultra 550B8.09 / 107.72$5.3822x more expensive
GLM-5.3 Flash8.59 / 108.38$15.0562x more expensive
Meta Muse Spark 1.38.06 / 107.84$18.0774x more expensive
Thinking Machines Inkling8.01 / 107.71$33.17136x more expensive
Grok 4.78.28 / 107.96$52.92217x more expensive
Moonshot Kimi K38.48 / 108.16$71.69295x more expensive
Qwen 3.8 Max8.07 / 107.77$107.70443x more expensive
GLM-5.38.88 / 108.66$175.06719x more expensive
Claude Opus 5.57.81 / 107.46$24.1499x more expensive
Tencent Hy4 Preview7.74 / 107.34$46.42191x more expensive
Gemini 3.8 Flash7.99 / 107.67$6.0125x more expensive
GPT-6 Sol7.18 / 106.88$6.9529x more expensive
Claude Haiku 5.57.20 / 106.86$0.743x more expensive
Qwen 3.8 Flash7.60 / 107.19$12.3551x more expensive
Gemini 3.5 Flash Lite7.07 / 106.79$1.797.4x more expensive
NVIDIA Nemotron-3 Nano 30B-A3B6.71 / 106.24$3.1713x more expensive
MiniMax M37.81 / 107.39$0.963.9x more expensive
NVIDIA Nemotron-3 Super 120B7.30 / 106.90$2.068.5x more expensive
Qwen 3.7 Plus7.82 / 107.43$5.3922x more expensive
Thinking Machines Inkling Small7.79 / 107.51$6.7228x more expensive
DeepSeek V4.1 Flash7.95 / 107.66$3.6615x more expensive

Cost breakdown

ModelQualityConfidenceCost / 1k runsOverpayMode
Xiaomi MiMo V2.6 Flash ★ Xiaomi MiMo8.17 / 10 CI [7.91, 8.44]HIGH$0.24best valuebatch
Tencent Hy3 OpenRouter8.24 / 10 CI [7.96, 8.52]HIGH$0.773.2xbatch
Xiaomi MiMo V2.6 Pro Xiaomi MiMo8.51 / 10 CI [8.25, 8.77]HIGH$1.104.5xbatch
NVIDIA Nemotron-3 Ultra 550B OpenRouter8.09 / 10 CI [7.72, 8.46]MEDIUM$5.3822xbatch
GLM-5.3 Flash Z.AI8.59 / 10 CI [8.38, 8.80]HIGH$15.0562xbatch
Meta Muse Spark 1.3 OpenRouter8.06 / 10 CI [7.84, 8.28]HIGH$18.0774xbatch
Thinking Machines Inkling OpenRouter8.01 / 10 CI [7.71, 8.30]HIGH$33.17136xbatch
Grok 4.7 xAI8.28 / 10 CI [7.96, 8.61]MEDIUM$52.92217xbatch
Moonshot Kimi K3 Moonshot AI8.48 / 10 CI [8.16, 8.81]MEDIUM$71.69295xbatch
Qwen 3.8 Max Alibaba Cloud (DashScope)8.07 / 10 CI [7.77, 8.37]MEDIUM$107.70443xbatch
GLM-5.3 best Z.AI8.88 / 10 CI [8.66, 9.11]HIGH$175.06719xbatch

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: 3272 input tokens → 6873 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 dependency ordering, narrative coherence, progression, local transitions, reader orientation, and use of every topic exactly once. Identifier completeness is deterministic.

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.

{
  "$defs": {
    "TopicSequenceItem": {
      "description": "Single topic in the recommended sequence.",
      "properties": {
        "topic_id": {
          "description": "The ID of the topic (exactly as provided in input)",
          "title": "Topic Id",
          "type": "integer"
        },
        "topic_name": {
          "description": "The name of the topic (exactly as provided in input, do not modify)",
          "title": "Topic Name",
          "type": "string"
        }
      },
      "required": [
        "topic_id",
        "topic_name"
      ],
      "title": "TopicSequenceItem",
      "type": "object"
    }
  },
  "description": "Output model for determining the optimal sequence of topics in a report.\nThe LLM analyzes topic content and determines the best reading order.",
  "properties": {
    "sequence_reasoning": {
      "default": "",
      "description": "Brief explanation of why this sequence was chosen (e.g., logical flow, building complexity, narrative arc).",
      "title": "Sequence Reasoning",
      "type": "string"
    },
    "sequenced_topics": {
      "description": "Ordered list of topics in the recommended reading sequence. First topic appears first in report.",
      "items": {
        "$ref": "#/$defs/TopicSequenceItem"
      },
      "title": "Sequenced Topics",
      "type": "array"
    }
  },
  "required": [
    "sequenced_topics"
  ],
  "title": "TopicSequenceOutput",
  "type": "object"
}

Prompt templates

The published template for this task.

default · LLMB_TOPIC_SEQUENCE_OPTIMIZATION_SYSTEM + LLMB_TOPIC_SEQUENCE_OPTIMIZATION_USER (0 calls in window)

System prompt

Return a permutation of the supplied topics only. Place necessary foundations before dependent analysis, group related material without collapsing distinct topics, and build a deliberate opening, progression, and conclusion suited to the subject. Use topic descriptions as evidence; do not rewrite, add, drop, or duplicate topics. 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 — subject_name: {subject_name}; topic_count: {topic_count}; topics_json: {topics_json}. Use only these inputs to complete the task defined by the system prompt.