NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 vs Qwen3.5 122B A10B
Wins 3 of 5 areas
Coding · Reasoning · Images and charts
Wins 1 of 5 areas
Following instructions
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is the stronger all-rounder.Qwen3.5 122B A10B is better at following instructions.
Scores updated · 32 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.
- CodingWriting and fixing software40NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF164 of 5 tests · 1 tie
- ReasoningHard problems that need careful thinking20NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF162 of 2 tests
- Images and chartsUnderstanding pictures, charts and video10NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF161 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 122B A10B1 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
Images and charts and following instructions rest on a single test each.
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+14.2points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+13.1points ahead
- Research-level physics problemsCritPt+10.3points ahead
Where Qwen3.5 122B A10B pulls ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+6.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+4.8points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
- Terminal-Bench 2.1NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 13.160.747.6+13.1
- LiveCodeBench v6NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 9.388.278.9+9.3
- SWE-bench ProNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 6.951.844.9+6.9
- SWE-bench MultilingualNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 5.767.762+5.7
- SWE-bench Verifiedtie71.172tie
AgentsEven
- BrowseCompNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 14.27863.8+14.2
- OSWorld-VerifiedQwen3.5 122B A10B by 6.951.158+6.9
ReasoningNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
- CritPtNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 10.310.90.6+10.3
- GPQA DiamondNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 3.889.585.7+3.8
Images and chartsNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
- CharXiv (RQ)NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 3.680.877.2+3.6
Following instructionsQwen3.5 122B A10B
- IFBenchQwen3.5 122B A10B by 4.870.975.7+4.8
Other results21 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.
- GDPval-AA v2NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 350 rating points1211861+350 rating
- DeepSWE [offline]NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 24.324.60.4+24.3
- WebVoyager [offline]NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 22.877.754.9+22.8
- BrowseComp [offline]NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 207858+20
- tau2-bench telecomQwen3.5 122B A10B by 1473.287.2+14
- tau2-bench retailNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 13.869.255.4+13.8
- tau2-bench airlineNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 1376.563.5+13
- BabyVisionQwen3.5 122B A10B by 10.629.640.2+10.6
- OCRBench v2, ZHQwen3.5 122B A10B by 8.159.167.3+8.1
- MATH-VisionQwen3.5 122B A10B by 878.286.2+8
- HLE, text-onlyNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 7.631.824.2+7.6
- SciCode, subtaskNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 7.347.139.8+7.3
- WMT24++NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 6.584.878.3+6.5
- LMArena v3 proxyNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 5.752.747+5.7
- MMLU-ProXQwen3.5 122B A10B by 5.376.982.2+5.3
- HLE, full setNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 4.829.224.4+4.8
- τ³-Bench BankingNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 4.718.914.2+4.7
- MMlongBench DocNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 3.862.859+3.8
- Terminal Bench 4 [offline]NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 110+1
- Video-MME v2tie32.932tie
- OCRBench v2_entie68.168.3tie
Questions people ask
Which is better, NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 or Qwen3.5 122B A10B?
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 wins three of the five areas where both have results: coding, reasoning and images and charts. Qwen3.5 122B A10B wins following instructions. They are level on agents.
Which is better for coding?
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16. It wins 4 of the 5 coding tests both models report; Qwen3.5 122B A10B wins none, and 1 is a tie.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 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.