Model comparison

GPT-6.1 Sol vs Sonar

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 38.5 on the Noometry Index. Sonar costs 4.0× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Sonar

Perplexity

38.5

Rank #187 Confirmed

Summary

The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 21.1.
Sonar is cheaper at $1 / $1 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
GPT-6.1 Sol accepts more context: 1.05M tokens versus 128K.

Side by side

GPT-6.1 Sol and Sonar specifications
	GPT-6.1 Sol	Sonar
Provider	OpenAI	Perplexity
Noometry Index	65.6	38.5
Released	2026-09-29	2024-01-01
Weights	Proprietary	Proprietary
Context window	1.05M	128K
Max output	128K	4K
Input $ / M tokens	$2	$1
Output $ / M tokens	$10	$1
Results tracked	34	7

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

Category by category

Coding GPT-6.1 Sol leads

GPT-6.1 Sol: 63.2 (#8), Sonar: 35.7 (#221)

Coding benchmarks
Benchmark	GPT-6.1 Sol	Sonar
DeepSWE	75.2%	—
FrontierCode	50.2%	—
LMArena WebDev	1755	—
SciCode	55.8%	—
LiveBench Coding	—	35.1%
LMArena Coding	1487	—

Agentic & Tool Use Not comparable

GPT-6.1 Sol: 39.6 (#26), Sonar: —

Agentic & Tool Use benchmarks
Benchmark	GPT-6.1 Sol	Sonar
APEX-Agents	60%	—
GDP.pdf	32%	—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Sonar: 21.1 (#227)

Reasoning benchmarks
Benchmark	GPT-6.1 Sol	Sonar
ARC-AGI-2	94.2%	—
NYT Connections (extended)	95.5%	—
ARC-AGI-1	98.5%	—
CritPt	31.7%	—
Chess Puzzles	61%	—
EBR-Bench	54.3%	—
LiveBench Reasoning	—	46.3%
LMArena Hard Prompts	1466	—
Mystery Game Puzzles	80%	—
LiveBench Data Analysis	—	37.9%
Epoch Capabilities Index	166.09	—
LiveBench	—	46.9%

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Sonar: 33.7 (#200)

Math benchmarks
Benchmark	GPT-6.1 Sol	Sonar
FrontierMath (Tiers 1-3)	93.7%	—
FrontierMath Tier 4	100%	—
OTIS Mock AIME 2024-2025	100%	—
ProofBench	99%	—
LiveBench Math	—	41.6%
LMArena Math	1464	—

Knowledge Not comparable

GPT-6.1 Sol: 71.8 (#4), Sonar: —

Knowledge benchmarks
Benchmark	GPT-6.1 Sol	Sonar
GPQA Diamond	95.4%	—
SimpleQA Verified	73.9%	—
LMArena Expert	1502	—

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Sonar: —

Multimodal benchmarks
Benchmark	GPT-6.1 Sol	Sonar
LMArena Vision	1288	—
Furniture Assembly	80%	—

Multilingual Not comparable

GPT-6.1 Sol: 54.3 (#46), Sonar: —

Multilingual benchmarks
Benchmark	GPT-6.1 Sol	Sonar
LMArena Non-English	1438	—
LMArena Chinese	1477	—
LMArena Russian	1455	—

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), Sonar: 71.4 (#150)

Instruction Following benchmarks
Benchmark	GPT-6.1 Sol	Sonar
LiveBench Instruction Following	—	76.2%
LMArena Instruction Following	1468	—

Long Context Not comparable

GPT-6.1 Sol: 44.9 (#54), Sonar: —

Long Context benchmarks
Benchmark	GPT-6.1 Sol	Sonar
LMArena Longer Query	1465	—

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Sonar: 52.6 (#167)

Writing & Preference benchmarks
Benchmark	GPT-6.1 Sol	Sonar
LMArena Text	1447	—
LMArena Creative Writing	1432	—
LMArena Multi-Turn	1449	—
LiveBench Language	—	44.1%

Frequently asked questions

Is GPT-6.1 Sol better than Sonar?

Which is cheaper, GPT-6.1 Sol or Sonar?

Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

Is GPT-6.1 Sol or Sonar better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 35.7 in the Noometry coding category.

Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 128K.

How many benchmarks do GPT-6.1 Sol and Sonar share?

0 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Sonar has 7.