Is Ministral 3 8B 2512 better than Solar Pro 4?

On accuracy they are statistically tied: Ministral 3 8B 2512 scored 42.5% and Solar Pro 4 45.0% 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 Solar Pro 4?

Ministral 3 8B 2512 is cheaper: $0.00027 per question as billed, against $0.0018. List prices: Ministral 3 8B 2512 $0.15 in / $0.15 out, Solar Pro 4 $0.15 in / $0.6 out per million tokens.

Which is faster, Ministral 3 8B 2512 or Solar Pro 4?

Ministral 3 8B 2512 is faster at 124 output tokens per second, against 91. Time to first token: 0.3 s for Ministral 3 8B 2512, 0.6 s for Solar Pro 4.

Which has the larger context window, Ministral 3 8B 2512 or Solar Pro 4?

Solar Pro 4, with 524k tokens against 262k.

Head to head · tested 27 Oct 2026

Ministral 3 8B 2512 vs Solar Pro 4: 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

UpstageSolar Pro 445.0% score · #49$0.0018 per question91 tok/s

Verdict

Built from the measurements below

Accuracy is too close to call: Ministral 3 8B 2512 scored 42.5% and Solar Pro 4 45.0% on the same 80 questions, a gap within what chance alone could produce.
Ministral 3 8B 2512 is 6.8× cheaper per question as billed ($0.00027 vs $0.0018), reasoning tokens included.
Ministral 3 8B 2512 generates text 1.4× faster: 124 tokens per second against 91.
Ministral 3 8B 2512 starts answering sooner: 0.3 s to the first token, against 0.6 s for Solar Pro 4.
Solar Pro 4 accepts more context: 524k tokens against 262k.

Which should you choose?

Choose Ministral 3 8B 2512 for the lower cost per correct answer ($0.00063 against $0.0041), faster streaming, a quicker first token, shorter outputs (about 1,496 tokens per question against 2,952) and open weights you can run yourself. Choose Solar Pro 4 for a 524k-token context window. The widest subject gap is in science: Solar Pro 4 answered 18 of 30 correctly, Ministral 3 8B 2512 10 of 30. 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	Solar Pro 4	Edge
Verification scoreHigher is better	42.5%	45.0%	Too close to call
Cost per questionLower is better	$0.00027	$0.0018	Ministral 3 8B 2512
Output speedHigher is better	124	91	Ministral 3 8B 2512
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	8.3 s	Ministral 3 8B 2512
Tokens per questionLower is better	1,496	2,952	Ministral 3 8B 2512
Context windowHigher is better	262k	524k	Solar Pro 4

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, Solar Pro 4 second

Verification scorehigher is better

Ministral 3 8B 251242.5%

Solar Pro 445.0%

Cost per questionlower is better

Ministral 3 8B 2512$0.00027

Solar Pro 4$0.0018

Output speedhigher is better

Ministral 3 8B 2512124

Solar Pro 491

Time to first tokenlower is better

Ministral 3 8B 25120.3 s

Solar Pro 40.6 s

End-to-end response timelower is better

Ministral 3 8B 25123.5 s

Solar Pro 48.3 s

Tokens per questionlower is better

Ministral 3 8B 25121,496

Solar Pro 42,952

Context windowhigher is better

Ministral 3 8B 2512262k

Solar Pro 4524k

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	Solar Pro 4
Science	30	10/30	18/30
Engineering	15	4/15	1/15
Medicine	11	5/11	5/11
Economics	9	7/9	5/9
Law	6	1/6	1/6
Humanities & social science	9	7/9	6/9
SuperGPQA dataset	50	10/50	14/50
MMLU-Pro dataset	30	24/30	22/30

Specifications and pricing

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

Specification	Ministral 3 8B 2512	Solar Pro 4
Creator	Mistral	Upstage
Released	2 Dec 2025	10 Aug 2026
Weights	Open weights	—
Reasoning	No	Yes
Input	text, image	text
Output	text	text
Context window	262k tokens	524k tokens
Knowledge cutoff	—	—
List price in / out per 1M	$0.15 / $0.15	$0.15 / $0.6
Blended price per 1M (3:1)	$0.15	$0.26
Cheapest host	Mistral · $0.15 / $0.15	Upstage · $0.15 / $0.6
Hosts on OpenRouter	1	1
Last tested	26 Oct 2026	26 Oct 2026

Compare any two models →

Ministral 3 8B 2512 vs Solar Pro 4: frequently asked questions

Is Ministral 3 8B 2512 better than Solar Pro 4?: On accuracy they are statistically tied: Ministral 3 8B 2512 scored 42.5% and Solar Pro 4 45.0% 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 Solar Pro 4?: Ministral 3 8B 2512 is cheaper: $0.00027 per question as billed, against $0.0018. List prices: Ministral 3 8B 2512 $0.15 in / $0.15 out, Solar Pro 4 $0.15 in / $0.6 out per million tokens.
Which is faster, Ministral 3 8B 2512 or Solar Pro 4?: Ministral 3 8B 2512 is faster at 124 output tokens per second, against 91. Time to first token: 0.3 s for Ministral 3 8B 2512, 0.6 s for Solar Pro 4.
Which has the larger context window, Ministral 3 8B 2512 or Solar Pro 4?: Solar Pro 4, with 524k tokens against 262k.