The Right-Sized LLM Benchmark Cheapest LLM that's good enough.

Thinking Machines Inkling Small at a glance

Good enough on 26/52 tasks at the 90% bar. Best value on 1 task. Best fit for: Structured Data & Fact Extraction, Financial Analysis & Trading Decisions, Infrastructure & Utility, Social & Promotional

Provider
OpenRouter
Model name
thinkingmachines/inkling-small
Cost mode:
Qualifies on
26 / 52 tasks (at 90% bar)
Best value on
1 tasks

Cost vs quality across all tasks

0%25%50%75%100%678910Quality score (6–10)Cost-efficiency vs best value (1.0 = best value)Public Response Generation — quality 8.16, 16.2x the cost of the best-value good-enough optionShort Promotional Teaser Generation — quality 8.51, 35.8x the cost of the best-value good-enough optionAtomic Fact Claim Extraction — quality 7.29, 9.8x the cost of the best-value good-enough optionCatalyst And Scenario Analysis — quality 7.97, this model IS the best-value good-enough option★Content Set Relevance Scoring — quality 6.68, 2.3x the cost of the best-value good-enough optionMulti Perspective Decision Synthesis — quality 8.51, 12.1x the cost of the best-value good-enough optionTopic Section Assignment — quality 8.11, 9.9x the cost of the best-value good-enough optionPublication Title Package Generation — quality 8.54, 1.7x the cost of the best-value good-enough optionVisual Theme Configuration Generation — quality 8.87, 8.3x the cost of the best-value good-enough optionResearch Region Identification — quality 8.50, 1.2x the cost of the best-value good-enough optionReport Outline Generation — quality 9.46, 5.8x the cost of the best-value good-enough optionEngagement Opportunity Triage — quality 8.78, 11.6x the cost of the best-value good-enough optionLanguage Identification — quality 9.83, 4.6x the cost of the best-value good-enough optionSocial Post Portfolio Selection — quality 8.74, 20.6x the cost of the best-value good-enough optionFactual Claim Refinement — quality 8.33, 14.8x the cost of the best-value good-enough optionBatch Text Translation — quality 8.51, 15.2x the cost of the best-value good-enough optionContent To Image Prompt Generation — quality 8.78, 6.1x the cost of the best-value good-enough optionProfiled Document Section Analysis — quality 8.73, 9.6x the cost of the best-value good-enough optionGenerated Content Relevance Scoring — quality 8.33, 5.2x the cost of the best-value good-enough optionPromotional Message Generation — quality 8.19, 7.9x the cost of the best-value good-enough optionCommunity Content Promotion Generation — quality 7.85, 4.1x the cost of the best-value good-enough optionStructured Content Summarization — quality 8.35, 3.2x the cost of the best-value good-enough optionSection Prompt Generation — quality 8.11, 4.3x the cost of the best-value good-enough optionTopic Cluster Labeling — quality 8.34, 2.9x the cost of the best-value good-enough optionModel Specific Prompt Adaptation — quality 8.44, 4.8x the cost of the best-value good-enough optionResearch Query Generation — quality 7.36, 9.8x the cost of the best-value good-enough option

within ~1.3× of the best-value model · 1.3–2× · >2× · ★ this model is the best-value pick on that task. Top-right = best quadrant. Only tasks where this model qualifies at the 90% bar are plotted.

Per-task breakdown

TaskCategoryQuality (% of best)ConfidenceOverpay
Catalyst And Scenario Analysis ★Financial Analysis & Trading Decisions91%MEDIUMbest value
Research Region IdentificationStructured Data & Fact Extraction96%HIGH1.2x
Publication Title Package GenerationContent Summarization & Synthesis93%RANKED1.7x
Content Set Relevance ScoringRelevance, Classification & Matching95%MEDIUM2.3x
Topic Cluster LabelingTopic Organization & Clustering94%MEDIUM2.9x
Structured Content SummarizationContent Summarization & Synthesis90%MEDIUM3.2x
Community Content Promotion GenerationSocial & Promotional Content91%MEDIUM4.1x
Section Prompt GenerationInfrastructure & Utility95%MEDIUM4.3x
Language IdentificationRelevance, Classification & Matching98%RANKED4.6x
Model Specific Prompt AdaptationInfrastructure & Utility96%MEDIUM4.8x
Generated Content Relevance ScoringRelevance, Classification & Matching91%MEDIUM5.2x
Report Outline GenerationLong-form Content Generation98%RANKED5.8x
Content To Image Prompt GenerationInfrastructure & Utility98%MEDIUM6.1x
Promotional Message GenerationSocial & Promotional Content94%MEDIUM7.9x
Visual Theme Configuration GenerationLong-form Content Generation94%HIGH8.3x
Profiled Document Section AnalysisFinancial Analysis & Trading Decisions96%RANKED9.6x
Atomic Fact Claim ExtractionStructured Data & Fact Extraction91%MEDIUM9.8x
Research Query GenerationInfrastructure & Utility90%MEDIUM9.8x
Topic Section AssignmentTopic Organization & Clustering93%MEDIUM9.9x
Engagement Opportunity TriageRelevance, Classification & Matching99%RANKED12x
Multi Perspective Decision SynthesisFinancial Analysis & Trading Decisions96%RANKED12x
Factual Claim RefinementInfrastructure & Utility97%MEDIUM15x
Batch Text TranslationInfrastructure & Utility91%MEDIUM15x
Public Response GenerationSocial & Promotional Content96%HIGH16x
Social Post Portfolio SelectionRelevance, Classification & Matching100%HIGH21x
Short Promotional Teaser GenerationSocial & Promotional Content97%RANKED36x

Overpay — how much more you pay by running this model instead of the best-value model that clears the quality bar on that task (marked ★). "16x" means you overpay 16× — the same output for 16× the best-value good-enough option; ★ means this model is that option (no overpayment). Confidence — how sure we are about the quality score (more judgments + more agreement = higher confidence): RANKED many independent judges scored this model's outputs and their agreement is very high (most confident) — HIGH many judges have scored it and they mostly agree (well-pinned) — MEDIUM enough judges have weighed in to publish, but they disagree more than we'd like (treat with a small grain of salt). LOW-confidence cells are hidden everywhere on the site. See the methodology for the exact thresholds.