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

NVIDIA Nemotron-3 Super 120B at a glance

Good enough on 8/52 tasks at the 90% bar. Best value on 1 task. Doesn't qualify on any: Financial Analysis & Trading Decisions, Infrastructure & Utility.

Provider
OpenRouter
Model name
nvidia/nemotron-3-super-120b-a12b
Cost mode:
Qualifies on
8 / 52 tasks (at 90% bar)
Best value on
1 tasks

Cost vs quality across all tasks

0%25%50%75%100%78910Quality score (7–10)Cost-efficiency vs best value (1.0 = best value)Short Promotional Teaser Generation — quality 8.15, 9.7x the cost of the best-value good-enough optionProfiled Document Structure Extraction — quality 8.84, this model IS the best-value good-enough option★Engagement Opportunity Triage — quality 8.50, 8.3x the cost of the best-value good-enough optionLanguage Identification — quality 9.91, 3.2x the cost of the best-value good-enough optionSocial Post Portfolio Selection — quality 8.10, 14.5x the cost of the best-value good-enough optionEvidence Grounded Claim Generation — quality 8.04, 2.7x the cost of the best-value good-enough optionGenerated Content Relevance Scoring — quality 8.58, 4.7x the cost of the best-value good-enough optionPromotional Message Generation — quality 7.90, 4.0x 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
Profiled Document Structure Extraction ★Structured Data & Fact Extraction93%MEDIUMbest value
Evidence Grounded Claim GenerationContent Summarization & Synthesis91%HIGH2.7x
Language IdentificationRelevance, Classification & Matching99%RANKED3.2x
Promotional Message GenerationSocial & Promotional Content91%HIGH4x
Generated Content Relevance ScoringRelevance, Classification & Matching93%MEDIUM4.7x
Engagement Opportunity TriageRelevance, Classification & Matching96%HIGH8.3x
Short Promotional Teaser GenerationSocial & Promotional Content93%RANKED9.7x
Social Post Portfolio SelectionRelevance, Classification & Matching92%MEDIUM14x

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.