Model comparison

DeepSeek-V3.1 vs Sonar

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.5 on the Noometry Index.

Last verified October 11, 2026. 0 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.8

Rank #108 Confirmed

Sonar

Perplexity

38.5

Rank #187 Confirmed

Summary

The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 52.6.
DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1 / $1 for Sonar.
DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.
DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1 and Sonar specifications
	DeepSeek-V3.1	Sonar
Provider	DeepSeek	Perplexity
Noometry Index	42.8	38.5
Released	2025-08-21	2024-01-01
Weights	Open	Proprietary
Context window	164K	128K
Max output	8K	4K
Input $ / M tokens	$0.25	$1
Output $ / M tokens	$0.95	$1
Results tracked	27	7

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 40.3 (#144), Sonar: 35.7 (#221)

Coding benchmarks
Benchmark	DeepSeek-V3.1	Sonar
WeirdML	38.4%	—
LiveBench Coding	—	35.1%
LMArena Coding	1417	—

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.9 (#110), Sonar: 21.1 (#227)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	Sonar
SimpleBench	40%	—
Kagi LLM Benchmark	53.2%	—
LiveBench Reasoning	—	46.3%
LMArena Hard Prompts	1417	—
DTBench	82.7%	—
LiveBench Data Analysis	—	37.9%
LMCA	24.3%	—
Epoch Capabilities Index	139.92	—
ForecastBench	58	—
LiveBench	—	46.9%

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 38.9 (#122), Sonar: 33.7 (#200)

Math benchmarks
Benchmark	DeepSeek-V3.1	Sonar
LiveBench Math	—	41.6%
LMArena Math	1420	—

Knowledge Not comparable

DeepSeek-V3.1: 43.7 (#90), Sonar: —

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	Sonar
Vectara Hallucination Rate	5.5%	—
LMArena Expert	1405	—

Multilingual Not comparable

DeepSeek-V3.1: 51.6 (#106), Sonar: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	Sonar
LMArena Non-English	1400	—
LMArena Chinese	1469	—
LMArena French	1447	—
LMArena German	1411	—
LMArena Japanese	1378	—
LMArena Korean	1337	—
LMArena Russian	1405	—
LMArena Spanish	1431	—

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 73.9 (#110), Sonar: 71.4 (#150)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	Sonar
LiveBench Instruction Following	—	76.2%
LMArena Instruction Following	1400	—

Long Context Not comparable

DeepSeek-V3.1: 36.3 (#232), Sonar: —

Long Context benchmarks
Benchmark	DeepSeek-V3.1	Sonar
Fiction.LiveBench	52.8%	—
LMArena Longer Query	1422	—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.3 (#98), Sonar: 52.6 (#167)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	Sonar
LMArena Text	1420	—
LMArena Creative Writing	1401	—
EQ-Bench Creative Writing	1436	—
LMArena Multi-Turn	1408	—
LiveBench Language	—	44.1%

Frequently asked questions

Is DeepSeek-V3.1 better than Sonar?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.5 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or Sonar?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Sonar lists at $1 and $1.

Is DeepSeek-V3.1 or Sonar better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 35.7 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 128K.

How many benchmarks do DeepSeek-V3.1 and Sonar share?

0 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Sonar has 7.