Noometry

Model comparison

GPT-4.1 mini vs Sonar

Sonar is the stronger model overall, scoring 38.5 to 33.6 on the Noometry Index.

Last verified . 0 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Sonar Perplexity

38.5

Rank #187 Confirmed

Summary

  • The widest gap is in reasoning, where Sonar leads 21.1 to 10.8.
  • GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1 / $1 for Sonar.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 128K.

Side by side

GPT-4.1 miniSonar
ProviderOpenAIPerplexity
Noometry Index33.638.5
Released2025-04-142024-01-01
WeightsProprietaryProprietary
Context window1.05M128K
Max output33K4K
Input $ / M tokens$0.40$1
Output $ / M tokens$1.60$1
Results tracked477

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

Category by category

Coding Sonar leads

GPT-4.1 mini: 30.6 (#293), Sonar: 35.7 (#221)

BenchmarkGPT-4.1 miniSonar
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
LiveBench Coding—35.1%
LMArena Coding1367—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), Sonar: —

BenchmarkGPT-4.1 miniSonar
Berkeley Function Calling Leaderboard50.5%—

Reasoning Sonar leads

GPT-4.1 mini: 10.8 (#340), Sonar: 21.1 (#227)

BenchmarkGPT-4.1 miniSonar
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
LiveBench Reasoning—46.3%
LMArena Hard Prompts1349—
Mystery Game Puzzles7%—
DTBench68.8%—
LiveBench Data Analysis—37.9%
LMCA21.1%—
Epoch Capabilities Index135.01—
LiveBench—46.9%

Math Sonar leads

GPT-4.1 mini: 24.1 (#270), Sonar: 33.7 (#200)

BenchmarkGPT-4.1 miniSonar
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
LiveBench Math—41.6%
LMArena Math1343—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge Not comparable

GPT-4.1 mini: 34.7 (#194), Sonar: —

BenchmarkGPT-4.1 miniSonar
GPQA Diamond65.8%—
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—
LMArena Expert1338—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), Sonar: —

BenchmarkGPT-4.1 miniSonar
LMArena Vision1181—

Multilingual Not comparable

GPT-4.1 mini: 45.7 (#166), Sonar: —

BenchmarkGPT-4.1 miniSonar
LMArena Non-English1318—
LMArena Chinese1329—
LMArena French1358—
LMArena German1351—
LMArena Japanese1290—
LMArena Korean1298—
LMArena Russian1324—
LMArena Spanish1319—

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), Sonar: 71.4 (#150)

BenchmarkGPT-4.1 miniSonar
LiveBench Instruction Following—76.2%
IFEval90.4%—
LMArena Instruction Following1333—

Long Context Not comparable

GPT-4.1 mini: 31.8 (#275), Sonar: —

BenchmarkGPT-4.1 miniSonar
Fiction.LiveBench44.4%—
LMArena Longer Query1344—

Writing & Preference Sonar leads

GPT-4.1 mini: 48.6 (#199), Sonar: 52.6 (#167)

BenchmarkGPT-4.1 miniSonar
LMArena Text1340—
LMArena Creative Writing1300—
EQ-Bench Creative Writing1147—
WildBench83.8%—
LMArena Multi-Turn1354—
LiveBench Language—44.1%

Frequently asked questions

Is GPT-4.1 mini better than Sonar?

Sonar is the stronger model overall, scoring 38.5 to 33.6 on the Noometry Index.

Which is cheaper, GPT-4.1 mini or Sonar?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Sonar lists at $1 and $1.

Is GPT-4.1 mini or Sonar better for coding?

Sonar scores higher on coding benchmarks: 35.7 versus 30.6 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 128K.

How many benchmarks do GPT-4.1 mini and Sonar share?

0 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Sonar has 7.

Related comparisons

Go deeper