Ember-1 vs Nemotron 3.5 Super VL (120B A12B): Specs & Benchmark Comparison
Ember-1 is developed by Fireworks AI, while Nemotron 3.5 Super VL (120B A12B) comes from NVIDIA. Ember-1 was released in September 2026, and Nemotron 3.5 Super VL (120B A12B) followed a month later in October 2026. Ember-1 is the larger model at roughly 2.8 trillion parameters, against 120 billion for Nemotron 3.5 Super VL (120B A12B).
The two models share 2 published benchmarks. Ember-1 leads on 2 of them. The widest gaps are on SWE-Bench Verified, where Ember-1 scores 92.2% against 71.1%; Terminal-Bench 2.1, where Ember-1 scores 82.0% against 66.7%. Averaged across everything we track, Ember-1 sits at 78.8% and Nemotron 3.5 Super VL (120B A12B) at 60.9%.
Nemotron 3.5 Super VL (120B A12B) is the cheaper API at $0.20 per million input tokens and $1 per million output tokens, roughly 15 times cheaper than Ember-1 at $3 and $15. Ember-1 takes the larger context window at 1M tokens, compared with 262K for Nemotron 3.5 Super VL (120B A12B). Ember-1 accepts text as input, while Nemotron 3.5 Super VL (120B A12B) accepts text, images, and video.
| Characteristic | Ember-1 | Nemotron 3.5 Super VL (120B A12B) |
|---|---|---|
| Company | Fireworks AI | NVIDIA |
| Release Date | September 23, 2026 | October 15, 2026 |
| Parameters | 2.8T | 120B |
| Multimodal | No | Yes |
| Context (input) | 1.0M | 262K |
| Context (output) | — | 262K |
| Input Price / 1M | $3.00 | $0.20 |
| Output Price / 1M | $15.00 | $1.00 |
| Average Score | 78.8% | 60.9% |
| Benchmarks | ||
| SWE-Bench Verified | 92.2% | 71.1% |
| Terminal-Bench 2.1 | 82.0% | 66.7% |
Visual Benchmark Comparison
Verdict
Nemotron 3.5 Super VL (120B A12B) leads in 2 out of 5 comparison categories.
Both models show comparable average scores: Ember-1 — 0.8, Nemotron 3.5 Super VL (120B A12B) — 0.6.
On SWE-Bench, both models are nearly equal: Ember-1 — 0.9, Nemotron 3.5 Super VL (120B A12B) — 0.7.
Nemotron 3.5 Super VL (120B A12B) is 15.0x cheaper: input $0.20/1M vs $3.00/1M tokens.
Ember-1 supports a larger context: 1M vs 262K tokens.
Nemotron 3.5 Super VL (120B A12B) is newer: released 10/15/2026 vs 9/23/2026.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — Ember-1 or Nemotron 3.5 Super VL (120B A12B)?
Which model is cheaper — Ember-1 or Nemotron 3.5 Super VL (120B A12B)?
Which has a larger context window — Ember-1 or Nemotron 3.5 Super VL (120B A12B)?
The Ember-1 and Nemotron 3.5 Super VL (120B A12B) comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Ember-1 or Nemotron 3.5 Super VL (120B A12B) page. See also the complete list of AI model comparisons.