Is Ministral 3 8B 2512 better than Nemotron 3.5 Super VL?

On accuracy they are statistically tied: Ministral 3 8B 2512 scored 42.5% and Nemotron 3.5 Super VL 40.0% on the same 80 questions from open datasets. Similar accuracy; Ministral 3 8B 2512 costs less per question.

Which is cheaper, Ministral 3 8B 2512 or Nemotron 3.5 Super VL?

Ministral 3 8B 2512 is cheaper: $0.00027 per question as billed, against $0.0013. List prices: Ministral 3 8B 2512 $0.15 in / $0.15 out, Nemotron 3.5 Super VL $0.15 in / $0.5 out per million tokens.

Which is faster, Ministral 3 8B 2512 or Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL is faster at 715 output tokens per second, against 124. Time to first token: 0.3 s for Ministral 3 8B 2512, 0.6 s for Nemotron 3.5 Super VL.

Which has the larger context window, Ministral 3 8B 2512 or Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL, with 1M tokens against 262k.

Head to head · tested 27 Oct 2026

Ministral 3 8B 2512 vs Nemotron 3.5 Super VL: accuracy, speed and price

Similar accuracy; Ministral 3 8B 2512 costs less per question.

MistralMinistral 3 8B 251242.5% score · #52$0.00027 per question124 tok/s

NVIDIANemotron 3.5 Super VL40.0% score · #58$0.0013 per question715 tok/s

Verdict

Built from the measurements below

Accuracy is too close to call: Ministral 3 8B 2512 scored 42.5% and Nemotron 3.5 Super VL 40.0% on the same 80 questions, a gap within what chance alone could produce.
Ministral 3 8B 2512 is 4.7× cheaper per question as billed ($0.00027 vs $0.0013), reasoning tokens included.
Nemotron 3.5 Super VL generates text 5.8× faster: 715 tokens per second against 124.
Ministral 3 8B 2512 starts answering sooner: 0.3 s to the first token, against 0.6 s for Nemotron 3.5 Super VL.
Nemotron 3.5 Super VL accepts more context: 1M tokens against 262k.

Which should you choose?

Choose Ministral 3 8B 2512 for the lower cost per correct answer ($0.00063 against $0.0032), a quicker first token and shorter outputs (about 1,496 tokens per question against 2,771). Choose Nemotron 3.5 Super VL for faster streaming, a 1M-token context window and more hosts to choose from on OpenRouter (9 against 1). The widest subject gap is in medicine: Ministral 3 8B 2512 answered 5 of 11 correctly, Nemotron 3.5 Super VL 2 of 11. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap +2.5 points (z = 0.32). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

Measure	Ministral 3 8B 2512	Nemotron 3.5 Super VL	Edge
Verification scoreHigher is better	42.5%	40.0%	Too close to call
Cost per questionLower is better	$0.00027	$0.0013	Ministral 3 8B 2512
Output speedHigher is better	124	715	Nemotron 3.5 Super VL
Time to first tokenLower is better	0.3 s	0.6 s	Ministral 3 8B 2512
End-to-end response timeLower is better	3.5 s	1.5 s	Nemotron 3.5 Super VL
Tokens per questionLower is better	1,496	2,771	Ministral 3 8B 2512
Context windowHigher is better	262k	1M	Nemotron 3.5 Super VL

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

Ministral 3 8B 2512 first, Nemotron 3.5 Super VL second

Verification scorehigher is better

Ministral 3 8B 251242.5%

Nemotron 3.5 Super VL40.0%

Cost per questionlower is better

Ministral 3 8B 2512$0.00027

Nemotron 3.5 Super VL$0.0013

Output speedhigher is better

Ministral 3 8B 2512124

Nemotron 3.5 Super VL715

Time to first tokenlower is better

Ministral 3 8B 25120.3 s

Nemotron 3.5 Super VL0.6 s

End-to-end response timelower is better

Ministral 3 8B 25123.5 s

Nemotron 3.5 Super VL1.5 s

Tokens per questionlower is better

Ministral 3 8B 25121,496

Nemotron 3.5 Super VL2,771

Context windowhigher is better

Ministral 3 8B 2512262k

Nemotron 3.5 Super VL1M

Score vs. cost per question

Both models in color, every other model in grey

Results by subject and dataset

Questions answered correctly. Small samples: a gap of one or two questions is noise.

Subject	Questions	Ministral 3 8B 2512	Nemotron 3.5 Super VL
Science	30	10/30	13/30
Engineering	15	4/15	4/15
Medicine	11	5/11	2/11
Economics	9	7/9	6/9
Law	6	1/6	0/6
Humanities & social science	9	7/9	7/9
SuperGPQA dataset	50	10/50	12/50
MMLU-Pro dataset	30	24/30	20/30

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

Specification	Ministral 3 8B 2512	Nemotron 3.5 Super VL
Creator	Mistral	NVIDIA
Released	2 Dec 2025	15 Oct 2026
Weights	Open weights	Open weights
Reasoning	No	Yes
Input	text, image	text, image, video
Output	text	text
Context window	262k tokens	1M tokens
Knowledge cutoff	—	—
List price in / out per 1M	$0.15 / $0.15	$0.15 / $0.5
Blended price per 1M (3:1)	$0.15	$0.24
Cheapest host	Mistral · $0.15 / $0.15	Darkbloom · $0.06 / $0.35
Hosts on OpenRouter	1	9
Last tested	26 Oct 2026	27 Oct 2026

Compare any two models →

Ministral 3 8B 2512 vs Nemotron 3.5 Super VL: frequently asked questions

Is Ministral 3 8B 2512 better than Nemotron 3.5 Super VL?: On accuracy they are statistically tied: Ministral 3 8B 2512 scored 42.5% and Nemotron 3.5 Super VL 40.0% on the same 80 questions from open datasets. Similar accuracy; Ministral 3 8B 2512 costs less per question.
Which is cheaper, Ministral 3 8B 2512 or Nemotron 3.5 Super VL?: Ministral 3 8B 2512 is cheaper: $0.00027 per question as billed, against $0.0013. List prices: Ministral 3 8B 2512 $0.15 in / $0.15 out, Nemotron 3.5 Super VL $0.15 in / $0.5 out per million tokens.
Which is faster, Ministral 3 8B 2512 or Nemotron 3.5 Super VL?: Nemotron 3.5 Super VL is faster at 715 output tokens per second, against 124. Time to first token: 0.3 s for Ministral 3 8B 2512, 0.6 s for Nemotron 3.5 Super VL.
Which has the larger context window, Ministral 3 8B 2512 or Nemotron 3.5 Super VL?: Nemotron 3.5 Super VL, with 1M tokens against 262k.