Model comparison

Mistral Large 3 vs Sonar

Mistral Large 3 and Sonar score almost the same on the Noometry Index (38.6 vs 37.8), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 0 shared benchmarks.

Mistral Large 3

Mistral AI

38.6

Rank #172 Confirmed

Sonar

Perplexity

37.8

Rank #184 Confirmed

Summary

The widest gap is in writing & preference, where Mistral Large 3 leads 60.2 to 52.6.
Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1 / $1 for Sonar.
Mistral Large 3 accepts more context: 262K tokens versus 128K.
Mistral Large 3 has downloadable open weights; the other is API-only.

Side by side

Mistral Large 3 and Sonar specifications
	Mistral Large 3	Sonar
Provider	Mistral AI	Perplexity
Noometry Index	38.6	37.8
Released	2025-12-02	2024-01-01
Weights	Open	Proprietary
Context window	262K	128K
Max output	8K	4K
Input $ / M tokens	$0.25	$1
Output $ / M tokens	$0.75	$1
Results tracked	24	7

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Sonar leads

Mistral Large 3: 34.1 (#230), Sonar: 35.1 (#217)

Coding benchmarks
Benchmark	Mistral Large 3	Sonar
LMArena WebDev	1230	—
LiveBench Coding	—	35.1%
LMArena Coding	1447	—

Reasoning Sonar leads

Mistral Large 3: 14.6 (#314), Sonar: 20.3 (#221)

Reasoning benchmarks
Benchmark	Mistral Large 3	Sonar
Kagi LLM Benchmark	50.9%	—
NYT Connections (extended)	7.5%	—
Thematic Generalization	23%	—
LiveBench Reasoning	—	46.3%
LMArena Hard Prompts	1429	—
LiveBench Data Analysis	—	37.9%
LiveBench	—	46.9%

Math Mistral Large 3 leads

Mistral Large 3: 36.0 (#131), Sonar: 31.3 (#197)

Math benchmarks
Benchmark	Mistral Large 3	Sonar
LiveBench Math	—	41.6%
LMArena Math	1415	—

Knowledge Not comparable

Mistral Large 3: 35.5 (#173), Sonar: —

Knowledge benchmarks
Benchmark	Mistral Large 3	Sonar
Vectara Hallucination Rate	14.5%	—
LMArena Expert	1421	—

Multimodal Not comparable

Mistral Large 3: 37.6 (#65), Sonar: —

Multimodal benchmarks
Benchmark	Mistral Large 3	Sonar
LMArena Vision	1222	—

Multilingual Not comparable

Mistral Large 3: 52.6 (#79), Sonar: —

Multilingual benchmarks
Benchmark	Mistral Large 3	Sonar
LMArena Non-English	1412	—
LMArena Chinese	1448	—
LMArena French	1456	—
LMArena German	1438	—
LMArena Japanese	1399	—
LMArena Korean	1384	—
LMArena Russian	1412	—
LMArena Spanish	1437	—

Instruction Following Mistral Large 3 leads

Mistral Large 3: 74.1 (#104), Sonar: 71.5 (#146)

Instruction Following benchmarks
Benchmark	Mistral Large 3	Sonar
LiveBench Instruction Following	—	76.2%
LMArena Instruction Following	1402	—

Long Context Not comparable

Mistral Large 3: 43.1 (#102), Sonar: —

Long Context benchmarks
Benchmark	Mistral Large 3	Sonar
LMArena Longer Query	1413	—

Writing & Preference Mistral Large 3 leads

Mistral Large 3: 60.2 (#100), Sonar: 52.6 (#166)

Writing & Preference benchmarks
Benchmark	Mistral Large 3	Sonar
LMArena Text	1427	—
LMArena Creative Writing	1385	—
EQ-Bench Creative Writing	1412	—
LMArena Multi-Turn	1429	—
LiveBench Language	—	44.1%

Frequently asked questions

Is Mistral Large 3 better than Sonar?

Mistral Large 3 and Sonar score almost the same on the Noometry Index (38.6 vs 37.8), so choose on price, context window or the category you care about most.

Which is cheaper, Mistral Large 3 or Sonar?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Sonar lists at $1 and $1.

Is Mistral Large 3 or Sonar better for coding?

Sonar scores higher on coding benchmarks: 35.1 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Mistral Large 3 and Sonar share?

0 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Sonar has 7.