- Score
- 8.6 (+0.87 points)
- Total Cost (Current Price)
- $0.061 · 86.1% cheaper
- Response Time (avg)
- 7.51s · 91.2% faster
NVIDIA
Release: 2026-10-15
Tested on: 2026-10-16 00:19
nvidia/nemotron-3.5-super-vl::medium
120B total (12B active)MoEOpen source
Summary
Nemotron 3.5 Super VL scores 7.7 on AI BENCHY and ranks #134. It has 9.8 reliability, a 72.5% pass rate, $0.437 total cost, and 84.94s average response time.
What makes Nemotron 3.5 Super VL unique: It stands out most in General Intelligence, where it ranks #3, while Coding is its weakest area at #16. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 7.5 (-0.17 points)
- Total Cost (Current Price)
- $0.000 · 100.0% cheaper
- Response Time (avg)
- 29.38s · 65.4% faster
- Score
- 9.4 (+1.65 points)
- Total Cost (Current Price)
- $0.183 · 58.2% cheaper
- Response Time (avg)
- 6.24s · 92.7% faster
Model facts
Researched on 2026-10-15
- Parameters
- 120B total (12B active)
- Architecture
- MoE
- Availability
- Open source
- License
- OpenMDW-1.1
Hybrid Mamba-2/Transformer MoE with a C-RADIO vision encoder. NVIDIA publishes weights, implementation, training data and recipes under the permissive OpenMDW-1.1 license. The model card documents reasoning off, medium and full; this route is the paid exact ID, not the free alias.
7.7
Consistency
8.3
9.8
$0.437
Total Output Tokens
792,033
Total Input Tokens
269,143
Input Price
$0.150 / 1M
Output Price
$0.500 / 1M
Cache Read Price
$0.020 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
5
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#134 Nemotron 3.5 Super VL
medium- Cost
- $0.004
- Time
- 68.1s
- Tokens
- 9,798 tok
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Nemotron 3.5 Super VLmediumFree AvailablevsMuse Glimmer 30BhighNemotron 3.5 Super VLmediumFree AvailablevsClaude Haiku 5.5mediumNemotron 3.5 Super VLmediumFree AvailablevsGPT-6 LunahighNemotron 3.5 Super VLmediumFree AvailablevsQwen3.5 Plus 2026-04-20mediumNemotron 3.5 Super VLmediumFree AvailablevsMuse WonderhighNemotron 3.5 Super VLmediumFree AvailablevsQwen3.7 FlashlowNemotron 3.5 Super VLmediumFree AvailablevsDeepSeek V4 Flash 0731mediumNemotron 3.5 Super VLmediumFree AvailablevsMuse Glimmer 30BmediumNemotron 3.5 Super VLmediumFree AvailablevsGrok 4.5lowNemotron 3.5 Super VLmediumFree AvailablevsMuse Wonderxhigh
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 10.0 | 10.0 | |
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 5.9 | 7.2 | |
| Combined | 6.4 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.6 | 7.2 | |
| General Intelligence | 6.5 | 3.4 | |
| Instructions following | 9.9 | 10.0 | |
| Puzzle Solving | 8.2 | 7.7 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |