Muse Spark Open vs Nemotron 3.5 Super VL
Wins 5 of 5 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 0 of 5 areas
—
Muse Spark Open is the stronger all-rounder.Nemotron 3.5 Super VL is cheaper.
Scores updated · 26 tests both models report · How we compare
Where each one wins
Tests won in each of the five areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- AgentsCarrying out multi-step tasks on its own30Muse Spark Open3 of 3 tests
- ReasoningHard problems that need careful thinking30Muse Spark Open3 of 3 tests
- CodingWriting and fixing software20Muse Spark Open2 of 2 tests
- FactsGetting facts right instead of making them up20Muse Spark Open2 of 2 tests
- Long documentsFinding answers in very long texts20Muse Spark Open2 of 2 tests
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Nemotron 3.5 Super VL costs 88% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Muse Spark Open pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+56points ahead
- Multi-step tasks using many real software toolsMCP Atlas+21.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16points ahead
Where Nemotron 3.5 Super VL pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMuse Spark Open
- Terminal-Bench 2.1Muse Spark Open by 15.776.460.7+15.7
- SciCodeMuse Spark Open by 10.658.447.8+10.6
AgentsMuse Spark Open
ReasoningMuse Spark Open
- ARC-AGI-2Muse Spark Open by 5657.51.5+56
- Humanity's Last ExamMuse Spark Open by 13.243.930.7+13.2
- CritPtMuse Spark Open by 4.314.910.6+4.3
FactsMuse Spark Open
- AA-Omniscience · AccuracyMuse Spark Open by 1639.323.3+16
- AA-Omniscience · Non-hallucinationMuse Spark Open by 11.775.964.2+11.7
Long documentsMuse Spark Open
- AA-LCRMuse Spark Open by 9.378.369+9.3
- LongBench v2Muse Spark Open by 6.668.762.1+6.6
Other results14 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- ARC-AGI-1Muse Spark Open by 66.38922.7+66.3
- SWEBench Pro v2 (Hard)Muse Spark Open by 45.689.744.1+45.6
- DeepSWE 1.1Muse Spark Open by 35.36024.7+35.3
- AA-OmniscienceMuse Spark Open by 28.924.6-4.2+28.9
- Chartography originalMuse Spark Open by 2635.79.7+26
- JobBenchMuse Spark Open by 25.361.836.5+25.3
- GDPval-AA 2.1Muse Spark Open by 239 rating points14011162+239 rating
- HLE-DiamondMuse Spark Open by 17.526.38.8+17.5
- CritPt v2 HardMuse Spark Open by 1629.513.5+16
- CritPt v2 FullMuse Spark Open by 15.752.636.9+15.7
- AA IntelligenceMuse Spark Open by 12.438.926.5+12.4
- Vals Finance IndexMuse Spark Open by 125341+12
- GDP (Surge AI)Muse Spark Open by 10.618.68+10.6
- Terminal-Bench-Science 0.1Muse Spark Open by 1.91.90+1.9
Questions people ask
Which is better, Muse Spark Open or Nemotron 3.5 Super VL?
Muse Spark Open wins all five areas where both have results: coding, agents, reasoning, facts and long documents. Nemotron 3.5 Super VL wins none, but costs 88% less.
Which is better for coding?
Muse Spark Open. It wins 2 of the 2 coding tests both models report; Nemotron 3.5 Super VL wins none.
Which is cheaper?
Muse Spark Open costs $1.25 per million input tokens and $4.25 per million output tokens; Nemotron 3.5 Super VL costs $0.15 and $0.50. That makes Nemotron 3.5 Super VL about 88% cheaper for the same work.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.