NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 vs Qwen3.8 Flash Next
Wins 0 of 5 areas
—
Wins 5 of 5 areas
Coding · Agents · Reasoning · Images and charts · Following instructions
Qwen3.8 Flash Next is the stronger all-rounder.
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 software05Qwen3.8 Flash Next5 of 5 tests
- AgentsCarrying out multi-step tasks on its own02Qwen3.8 Flash Next2 of 2 tests
- ReasoningHard problems that need careful thinking01Qwen3.8 Flash Next1 of 2 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video01Qwen3.8 Flash Next1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.8 Flash Next1 of 1 test
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 Qwen3.8 Flash Next pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+25.4points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+13.3points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+11points ahead
Where NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 pulls ahead
No clear win on a test scored out of 100.
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.
CodingQwen3.8 Flash Next
- Terminal-Bench 2.1Qwen3.8 Flash Next by 25.460.786.1+25.4
- SWE-bench MultilingualQwen3.8 Flash Next by 13.367.781+13.3
- SWE-bench ProQwen3.8 Flash Next by 10.751.862.5+10.7
- SWE-bench VerifiedQwen3.8 Flash Next by 7.671.178.7+7.6
- LiveCodeBench v6Qwen3.8 Flash Next by 3.788.291.9+3.7
AgentsQwen3.8 Flash Next
- BrowseCompQwen3.8 Flash Next by 117889+11
- OSWorld-VerifiedQwen3.8 Flash Next by 4.751.155.8+4.7
ReasoningQwen3.8 Flash Next
- GPQA DiamondQwen3.8 Flash Next by 2.889.592.3+2.8
- CritPttie10.911.1tie
Images and chartsQwen3.8 Flash Next
- CharXiv (RQ)Qwen3.8 Flash Next by 9.880.890.6+9.8
Following instructionsQwen3.8 Flash Next
- IFBenchQwen3.8 Flash Next by 10.470.981.3+10.4
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 v2Qwen3.8 Flash Next by 350 rating points12111561+350 rating
- DeepSWE [offline]Qwen3.8 Flash Next by 30.924.655.6+30.9
- τ³-Bench BankingQwen3.8 Flash Next by 25.618.944.5+25.6
- Terminal Bench 4 [offline]Qwen3.8 Flash Next by 19.7120.7+19.7
- LMArena v3 proxyNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 by 17.552.735.2+17.5
- MATH-VisionQwen3.8 Flash Next by 17.578.295.7+17.5
- BabyVisionQwen3.8 Flash Next by 17.229.646.8+17.2
- tau2-bench telecomQwen3.8 Flash Next by 17.273.290.4+17.2
- WebVoyager [offline]Qwen3.8 Flash Next by 12.777.790.4+12.7
- Video-MME v2Qwen3.8 Flash Next by 12.232.945.1+12.2
- BrowseComp [offline]Qwen3.8 Flash Next by 117889+11
- HLE, full setQwen3.8 Flash Next by 9.629.238.8+9.6
- OCRBench v2, ZHQwen3.8 Flash Next by 9.159.168.3+9.1
- HLE, text-onlyQwen3.8 Flash Next by 7.831.839.6+7.8
- MMLU-ProXQwen3.8 Flash Next by 6.176.983+6.1
- MMlongBench DocQwen3.8 Flash Next by 5.162.867.9+5.1
- tau2-bench airlineQwen3.8 Flash Next by 4.376.580.8+4.3
- tau2-bench retailQwen3.8 Flash Next by 2.469.271.6+2.4
- WMT24++Qwen3.8 Flash Next by 1.484.886.2+1.4
- SciCode, subtasktie47.146.6tie
- OCRBench v2_entie68.167.9tie
Questions people ask
Which is better, NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 or Qwen3.8 Flash Next?
Qwen3.8 Flash Next wins all five areas where both have results: coding, agents, reasoning, images and charts and following instructions. NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 wins none.
Which is better for coding?
Qwen3.8 Flash Next. It wins 5 of the 5 coding tests both models report; NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 wins none.
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.