Model comparison

Mistral Small 3.1 vs Sonar

Sonar is the stronger model overall, scoring 38.5 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 2.5× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

Mistral Small 3.1

Mistral AI

31.7

Rank #269 Confirmed

Sonar

Perplexity

38.5

Rank #187 Confirmed

Summary

The widest gap is in math, where Sonar leads 33.7 to 14.7.
Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $1 / $1 for Sonar.
Mistral Small 3.1 has downloadable open weights; the other is API-only.

Side by side

Mistral Small 3.1 and Sonar specifications
	Mistral Small 3.1	Sonar
Provider	Mistral AI	Perplexity
Noometry Index	31.7	38.5
Released	2025-03-17	2024-01-01
Weights	Open	Proprietary
Context window	128K	128K
Max output	102K	4K
Input $ / M tokens	$0.35	$1
Output $ / M tokens	$0.56	$1
Results tracked	28	7

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

Category by category

Coding Mistral Small 3.1 leads

Mistral Small 3.1: 38.3 (#179), Sonar: 35.7 (#221)

Coding benchmarks
Benchmark	Mistral Small 3.1	Sonar
LiveBench Coding	—	35.1%
LMArena Coding	1309	—

Reasoning Sonar leads

Mistral Small 3.1: 19.7 (#254), Sonar: 21.1 (#227)

Reasoning benchmarks
Benchmark	Mistral Small 3.1	Sonar
Chess Puzzles	1%	—
LiveBench Reasoning	—	46.3%
LMArena Hard Prompts	1278	—
LiveBench Data Analysis	—	37.9%
Epoch Capabilities Index	127.48	—
LiveBench	—	46.9%

Math Sonar leads

Mistral Small 3.1: 14.7 (#301), Sonar: 33.7 (#200)

Math benchmarks
Benchmark	Mistral Small 3.1	Sonar
OTIS Mock AIME 2024-2025	3.9%	—
Omni-MATH	24.8%	—
LiveBench Math	—	41.6%
LMArena Math	1262	—

Knowledge Not comparable

Mistral Small 3.1: 22.6 (#271), Sonar: —

Knowledge benchmarks
Benchmark	Mistral Small 3.1	Sonar
GPQA Diamond	41.9%	—
MMLU-Pro	61%	—
GPQA (HELM)	39.2%	—
LMArena Expert	1257	—

Multimodal Not comparable

Mistral Small 3.1: 33.2 (#99), Sonar: —

Multimodal benchmarks
Benchmark	Mistral Small 3.1	Sonar
LMArena Vision	1136	—

Multilingual Not comparable

Mistral Small 3.1: 41.2 (#209), Sonar: —

Multilingual benchmarks
Benchmark	Mistral Small 3.1	Sonar
LMArena Non-English	1255	—
LMArena Chinese	1253	—
LMArena French	1273	—
LMArena German	1266	—
LMArena Japanese	1208	—
LMArena Korean	1206	—
LMArena Russian	1263	—
LMArena Spanish	1283	—

Instruction Following Sonar leads

Mistral Small 3.1: 63.6 (#230), Sonar: 71.4 (#150)

Instruction Following benchmarks
Benchmark	Mistral Small 3.1	Sonar
LiveBench Instruction Following	—	76.2%
IFEval	75%	—
LMArena Instruction Following	1264	—

Long Context Not comparable

Mistral Small 3.1: 39.5 (#178), Sonar: —

Long Context benchmarks
Benchmark	Mistral Small 3.1	Sonar
LMArena Longer Query	1299	—

Writing & Preference Sonar leads

Mistral Small 3.1: 37.0 (#259), Sonar: 52.6 (#167)

Writing & Preference benchmarks
Benchmark	Mistral Small 3.1	Sonar
LMArena Text	1277	—
LMArena Creative Writing	1253	—
EQ-Bench Creative Writing	761	—
WildBench	78.8%	—
LMArena Multi-Turn	1270	—
LiveBench Language	—	44.1%

Frequently asked questions

Is Mistral Small 3.1 better than Sonar?

Which is cheaper, Mistral Small 3.1 or Sonar?

Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Sonar lists at $1 and $1.

Is Mistral Small 3.1 or Sonar better for coding?

Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 35.7 in the Noometry coding category.

Which has the bigger context window?

Both accept 128K tokens.

How many benchmarks do Mistral Small 3.1 and Sonar share?

0 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Sonar has 7.