Enter opens the highlighted result. Esc closes.

Mistral Large 3 2512 vs Sonar Deep Research

Updated October 21, 2026. 0 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Mistral Large 3 2512 Replace Sonar Deep Research
Mistral Large 3 2512Mistral AI
Coding
No data
Overall
9.3
Output $/M
$1.50
Sonar Deep ResearchPerplexity
Coding
No data
Overall
No data
Output $/M
$8.00
vs $1.50 vs $8.00 per 1M output tokens. Mistral Large 3 2512 is 5.3x cheaper.

Decision reading

Neither model has a coding score yet, so the two cannot be ranked on coding.

Mistral Large 3 2512 has the edge where output tokens cost 5.3x less, and where the context window is larger, 262K against 128K tokens.

Model AMistral Large 3 2512Mistral AINot benchmarked1 independent benchmark$0.77 per solved taskModel BSonar Deep ResearchPerplexityNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
0
Mistral Large 3 2512 only
28
Sonar Deep Research only
0
Like-for-like categories
0 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Mistral Large 3 2512 not benchmarked, Sonar Deep Research not benchmarked.
Widest category
No category has a result for both models.
Widest single gap
No benchmark has a result for both models.
Output price
Mistral Large 3 2512 $1.50 against Sonar Deep Research $8.00 per million output tokens, 5.3x apart.
Context window
Mistral Large 3 2512 takes 262K tokens, Sonar Deep Research 128K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards, none shared
Coding benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
AA Coding Index20.1Not measuredOnly Mistral Large 3 2512 measured
LiveCodeBench (Vals AI)55.3%Not measuredOnly Mistral Large 3 2512 measured
SWE-bench Verified (Vals AI)41.4%Not measuredOnly Mistral Large 3 2512 measured
ALE-Bench264.7Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 34 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Intelligence benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
AA Intelligence Index9.3Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
AA Agentic Index1.0Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 38 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Reasoning benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
GPQA Diamond68.4%Not measuredOnly Mistral Large 3 2512 measured
MMMU Pro (Vals AI)66.2%Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 19 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Math benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
AIME42.9%Not measuredOnly Mistral Large 3 2512 measured
MGSM (Vals AI)85.4%Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 11 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Knowledge benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
MMLU Pro79.8%Not measuredOnly Mistral Large 3 2512 measured
LegalBench (Vals AI)79.1%Not measuredOnly Mistral Large 3 2512 measured
CaseLaw (Vals AI)61.4%Not measuredOnly Mistral Large 3 2512 measured
CorpFin (Vals AI)61.0%Not measuredOnly Mistral Large 3 2512 measured
TaxEval (Vals AI)73.1%Not measuredOnly Mistral Large 3 2512 measured
MortgageTax (Vals AI)52.1%Not measuredOnly Mistral Large 3 2512 measured
MedQA (Vals AI)82.2%Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
Design Arena: websites1162Not measuredOnly Mistral Large 3 2512 measured
Design Arena: UI components1102Not measuredOnly Mistral Large 3 2512 measured
Design Arena: game dev1080Not measuredOnly Mistral Large 3 2512 measured
Design Arena: data viz1136Not measuredOnly Mistral Large 3 2512 measured
Design Arena: 3D1099Not measuredOnly Mistral Large 3 2512 measured
Design Arena: all code categories1142Not measuredOnly Mistral Large 3 2512 measured
Design Arena: SVG993Not measuredOnly Mistral Large 3 2512 measured
Design Arena: ASCII art1069Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
General benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
SAGE (Vals AI)24.6%Not measuredOnly Mistral Large 3 2512 measured
DTBench65.1%Not measuredOnly Mistral Large 3 2512 measured
LMCA16.7%Not measuredOnly Mistral Large 3 2512 measured
Neither model has a result on the other 43 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mistral Large 3 2512 and Sonar Deep Research
BenchmarkMistral Large 3 2512Sonar Deep ResearchLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Mistral Large 3 2512$0.0013Fits in one request
Sonar Deep Research$0.0060Fits in one request

Mistral Large 3 2512 costs less

Repository review

50K input + 3K output tokens

Mistral Large 3 2512$0.029Fits in one request
Sonar Deep Research$0.124Fits in one request

Mistral Large 3 2512 costs less

Agent loop

200K input + 10K output tokens

Mistral Large 3 2512$0.115Fits in one request
Sonar Deep Research$0.480Exceeds the context window

Mistral Large 3 2512 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Mistral Large 3 2512 and Sonar Deep Research
SpecificationMistral Large 3 2512Perplexity Sonar Deep Research
MakerMistral AIPerplexity
WeightsNo public weights listedNo public weights listed
ReleasedDecember 1, 2025March 7, 2025
Context window262K128K
Input $/Mtok$0.50$2.00
Output $/Mtok$1.50$8.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$0.77Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Large 3 2512 better than Sonar Deep Research for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Mistral Large 3 2512 has the edge where output tokens cost 5.3x less, and where the context window is larger, 262K against 128K tokens.

Which is cheaper, Mistral Large 3 2512 or Sonar Deep Research?

Mistral Large 3 2512 costs $0.50 per million input tokens and $1.50 per million output tokens; Sonar Deep Research costs $2.00 and $8.00. Cost per solved task is known for Mistral Large 3 2512 only.

Which has the bigger context window, Mistral Large 3 2512 or Sonar Deep Research?

Mistral Large 3 2512, with 262K tokens against 128K.

How many benchmarks is the Mistral Large 3 2512 vs Sonar Deep Research comparison based on?

0 benchmarks have a result for both models as of October 21, 2026. Mistral Large 3 2512's coding index rests on 1 independent benchmark and Sonar Deep Research's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next