CODING
71.1
Media Cap quality axis
NVIDIA · Open weightsNemotron 3.5 Super VL 120B A12B
Active
Model portfolio
Nemotron 3.5 Super VL 120B A12B
Tap a star to rate
NVIDIA · Open · Context 262K tokens
Language Cap
62
Cadle Language Cap 62 · 52%
Benchmark average
79.2
Not enough benchmark results yet
Pricing
$0.20
$1.00 / 1M out · 41.0 pts/$
CADLE CAP vs MODEL MATRIX
Cadle Cap ranks models on every published score we have for them — harder benchmarks weigh more. Missing tests are skipped, not zeroed. It answers who is stronger than whom in today's pool.
Model Matrix is the datasheet: Overall, Intelligence, Coding, Agentic, MMLU, GPQA, Math, LiveCodeBench, HumanEval, Reason, ARC-AGI. A dash means unmeasured. AVG is an importance-weighted mean of that model's filled cells only.
MODEL MATRIX · TRUTH CENTER CELLS
Overall
49.2
Intelligence
No data yet
Coding
71.1
Agentic
78.0
MMLU
51.2
GPQA
89.5
Math
88.4
LiveCodeBench
88.2
HumanEval
No data yet
Reason
72.1
ARC-AGI
No data yet
Coverage AVG
79.2
Cadle Cap ranks models with within-benchmark percentiles so ARC-AGI ~40 and MMLU ~90 never compete raw. Coverage AVG is an importance-weighted mean of filled expert cells only — blanks are skipped, not zeroed.
ANALYSIS · TRUTH CENTER
Hard benches (GPQA · ARC-AGI · LCB · Agentic) sit left — a mid-40 on ARC-AGI can still be frontier. Broader benches on the right are easier and often higher.
CADLE INSIGHTS
Only measured signals
AGENTIC
77.5
Media Cap quality axis
MATH
89.4
Media Cap quality axis
KNOWLEDGE
74.8
Media Cap quality axis
MATRIX OVERALL
49.2
AVG 79.2 across matrix cells
STRONGEST SIGNAL
Coding
Cap axis 71.1
BLENDED $/1M
$1.20
In $0.20 · Out $1.00
VALUE INDEX
41.0
Quality ÷ blended $/1M (higher is better)
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 49.2
- Cap Coding
- 67.2
- Matrix Coding
- 71.1
- Input $/1M
- $0.20
- Output $/1M
- $1.00
- Value pts/$
- 41.02
DESCRIPTION + DETAILS
PROVIDER
NVIDIA
CONTEXT
262K tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — not marketing copy.
No reviews yet
WRITE A REVIEW
Tap a star to rate
Stored on this device · synced when signed in
No operator notes yet
First review sets the tone for how teams evaluate Nemotron 3.5 Super VL 120B A12B.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | NVIDIA |
| Release | |
| Input / 1M | $0.20 |
| Output / 1M | $1.00 |
| Context | 262K tokens |
| Cadle Cap | 62 |
| Cap board | Cadle Language Cap 62 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
NVIDIA listing
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall49.2
Coding71.1
Agentic78
MMLU51.2
GPQA89.5
Math88.4
LiveCodeBench88.2