Cost mode:

Category: Infrastructure & Utility · Typical I/O: 1590→1073 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: Moonshot Kimi K3 at 9.25 / 10. Quality bar at 90%: 8.32.

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 Flash8.32 / 107.93$0.16best value
GPT-6 Luna8.63 / 108.33$0.251.6x more expensive
Xiaomi MiMo V2.6 Pro8.88 / 108.63$0.583.6x more expensive
Gemini 3.5 Flash Lite8.59 / 108.28$0.664.2x more expensive
MiniMax M38.79 / 108.57$1.117x more expensive
DeepSeek V4.1 Flash8.67 / 108.31$2.1313x more expensive
Tencent Hy38.37 / 108.06$2.7918x more expensive
Qwen 3.7 Plus8.92 / 108.78$3.2721x more expensive
Gemini 3.8 Flash9.01 / 108.78$3.6323x more expensive
Thinking Machines Inkling Small8.48 / 108.14$4.3928x more expensive
GPT-6 Sol8.91 / 108.70$4.7630x more expensive
Claude Sonnet 5.58.86 / 108.56$5.7736x more expensive
GLM-5.3 Flash8.92 / 108.67$6.3640x more expensive
Meta Muse Spark 1.38.91 / 108.72$8.7555x more expensive
Claude Opus 5.59.04 / 108.83$12.6580x more expensive
Thinking Machines Inkling8.58 / 108.16$17.05108x more expensive
Moonshot Kimi K39.25 / 109.08$28.51180x more expensive
Grok 4.78.67 / 108.27$33.63212x more expensive
Qwen 3.8 Max8.46 / 108.07$37.65238x more expensive
GLM-5.38.92 / 108.61$72.87460x more expensive
NVIDIA Nemotron-3 Nano 30B-A3B7.32 / 106.91$0.644x more expensive
NVIDIA Nemotron-3 Super 120B7.98 / 107.60$2.2914x more expensive
Qwen 3.8 Flash8.15 / 107.69$6.9544x more expensive

Cost breakdown

ModelQualityConfidenceCost / 1k runsOverpayMode
Xiaomi MiMo V2.6 Flash ★ Xiaomi MiMo8.32 / 10 CI [7.93, 8.72]MEDIUM$0.16best valuebatch
GPT-6 Luna OpenAI8.63 / 10 CI [8.33, 8.92]HIGH$0.251.6xbatch
Xiaomi MiMo V2.6 Pro Xiaomi MiMo8.88 / 10 CI [8.63, 9.13]HIGH$0.583.6xbatch
Gemini 3.5 Flash Lite Gemini8.59 / 10 CI [8.28, 8.91]MEDIUM$0.664.2xbatch
MiniMax M3 OpenRouter8.79 / 10 CI [8.57, 9.01]HIGH$1.117xbatch
DeepSeek V4.1 Flash DeepSeek8.67 / 10 CI [8.31, 9.03]MEDIUM$2.1313xbatch
Tencent Hy3 OpenRouter8.37 / 10 CI [8.06, 8.67]MEDIUM$2.7918xbatch
Qwen 3.7 Plus Alibaba Cloud (DashScope)8.92 / 10 CI [8.78, 9.06]RANKED$3.2721xbatch
Gemini 3.8 Flash Gemini9.01 / 10 CI [8.78, 9.25]HIGH$3.6323xbatch
Thinking Machines Inkling Small OpenRouter8.48 / 10 CI [8.14, 8.83]MEDIUM$4.3928xbatch
GPT-6 Sol OpenAI8.91 / 10 CI [8.70, 9.13]HIGH$4.7630xbatch
Claude Sonnet 5.5 Anthropic8.86 / 10 CI [8.56, 9.15]HIGH$5.7736xbatch
GLM-5.3 Flash Z.AI8.92 / 10 CI [8.67, 9.17]HIGH$6.3640xbatch
Meta Muse Spark 1.3 OpenRouter8.91 / 10 CI [8.72, 9.11]RANKED$8.7555xbatch
Claude Opus 5.5 Anthropic9.04 / 10 CI [8.83, 9.25]HIGH$12.6580xbatch
Thinking Machines Inkling OpenRouter8.58 / 10 CI [8.16, 9.00]MEDIUM$17.05108xbatch
Moonshot Kimi K3 best Moonshot AI9.25 / 10 CI [9.08, 9.41]RANKED$28.51180xbatch
Grok 4.7 xAI8.67 / 10 CI [8.27, 9.07]MEDIUM$33.63212xbatch
Qwen 3.8 Max Alibaba Cloud (DashScope)8.46 / 10 CI [8.07, 8.85]MEDIUM$37.65238xbatch
GLM-5.3 Z.AI8.92 / 10 CI [8.61, 9.23]MEDIUM$72.87460xbatch

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: 1590 input tokens → 1073 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 semantic fidelity, fluency in the target language, preservation of tone and qualifiers, exact handling of protected tokens, item alignment, and avoidance of added or omitted meaning.

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.

{
  "$defs": {
    "BatchTranslationItem": {
      "description": "One translated item in a batch translation result.",
      "properties": {
        "index": {
          "description": "0-based index of this item in the input list. Must match the input order.",
          "title": "Index",
          "type": "integer"
        },
        "translated_text": {
          "description": "Translated text for the item at this index.",
          "title": "Translated Text",
          "type": "string"
        }
      },
      "required": [
        "index",
        "translated_text"
      ],
      "title": "BatchTranslationItem",
      "type": "object"
    }
  },
  "description": "Batched translation: translate a list of texts in a single LLM call.\n\nThe output items list MUST be the same length as the input list, with index\nvalues 0..N-1 in order. Each translated_text corresponds to the input at the\nsame index.",
  "properties": {
    "items": {
      "description": "Translations in the same order as the input list. Length must equal the input list length.",
      "items": {
        "$ref": "#/$defs/BatchTranslationItem"
      },
      "title": "Items",
      "type": "array"
    }
  },
  "required": [
    "items"
  ],
  "title": "BatchTranslationResult",
  "type": "object"
}

Prompt templates

The published template for this task.

default · LLMB_BATCH_TEXT_TRANSLATION_SYSTEM + LLMB_BATCH_TEXT_TRANSLATION_USER (6386 calls in window)

System prompt

Translate meaning rather than word order. Preserve names, numbers, dates, URLs, handles, hashtags, code, markup, and caller-defined protected tokens exactly unless transliteration is requested. Keep item order and identifiers, reproduce ambiguity rather than resolving it with new facts, and return only the configured output language and schema. 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 — source_language: {source_language}; target_language: {target_language}; items_json: {items_json}; input_text: {input_text}. Use only these inputs to complete the task defined by the system prompt.