Noometry

Model comparison

GPT-5.2 Pro vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 61.8 to 52.3 on the Noometry Index.

Last verified . 6 shared benchmarks.

GPT-5.2 Pro OpenAI

52.3

Rank #39 Reported

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 6 benchmarks with published results for both. GPT-5.2 Pro scores higher in 0 categories and GPT-6 Sol in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 51.5.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 46% for GPT-5.2 Pro and 90% for GPT-6 Sol.
  • GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
  • GPT-6 Sol accepts more context: 1.05M tokens versus 400K.

Side by side

GPT-5.2 ProGPT-6 Sol
ProviderOpenAIOpenAI
Noometry Index52.361.8
Released2025-12-112026-09-22
WeightsProprietaryProprietary
Context window400K1.05M
Max output128K128K
Input $ / M tokens$21$2
Output $ / M tokens$168$10
Results tracked845

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

Category by category

Coding Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 60.1 (#11)

BenchmarkGPT-5.2 ProGPT-6 Sol
DeepSWE—68.8%
FrontierCode—49.3%
LMArena WebDev—1688
SciCode—57.6%
LMArena Coding—1447
ALE-Bench—2,462

Agentic & Tool Use Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 37.2 (#36)

BenchmarkGPT-5.2 ProGPT-6 Sol
APEX-Agents—54.3%
GDP.pdf—26.4%
Vending-Bench 2—14,428

Reasoning GPT-6 Sol leads

GPT-5.2 Pro: 51.5 (#33), GPT-6 Sol: 74.0 (#9)

BenchmarkGPT-5.2 ProGPT-6 Sol
ARC-AGI-254.2%89.6%
NYT Connections (extended)79.3%90.1%
ARC-AGI-190.5%95.5%
Epoch Capabilities Index155.4162.72
SimpleBench57.4%—
CritPt—30.9%
EBR-Bench—53.3%
LMArena Hard Prompts—1418
Mystery Game Puzzles—56%
DTBench—97.3%
LMCA—59.1%

Math GPT-6 Sol leads

GPT-5.2 Pro: 65.3 (#29), GPT-6 Sol: 87.2 (#7)

BenchmarkGPT-5.2 ProGPT-6 Sol
FrontierMath (Tiers 1-3)74%89.8%
FrontierMath Tier 446%90%
OTIS Mock AIME 2024-2025—100%
ProofBench—83%
LMArena Math—1402
FrontierMath Tier 4 (v1)31.3%—

Knowledge Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 64.8 (#15)

BenchmarkGPT-5.2 ProGPT-6 Sol
GPQA Diamond—94.3%
SimpleQA Verified—60.7%
Vectara Hallucination Rate—6.5%
LMArena Expert—1439

Multimodal Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 47.6 (#10)

BenchmarkGPT-5.2 ProGPT-6 Sol
LMArena Vision—1245
Blueprint-Bench 2—36.9%
Furniture Assembly—58.3%

Multilingual Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 50.5 (#118)

BenchmarkGPT-5.2 ProGPT-6 Sol
LMArena Non-English—1385
LMArena Chinese—1405
LMArena French—1410
LMArena German—1390
LMArena Japanese—1385
LMArena Korean—1341
LMArena Russian—1401
LMArena Spanish—1384

Instruction Following Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 74.5 (#94)

BenchmarkGPT-5.2 ProGPT-6 Sol
LMArena Instruction Following—1412

Long Context Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 43.1 (#108)

BenchmarkGPT-5.2 ProGPT-6 Sol
LMArena Longer Query—1411

Writing & Preference Not comparable

GPT-5.2 Pro: —, GPT-6 Sol: 71.9 (#18)

BenchmarkGPT-5.2 ProGPT-6 Sol
LMArena Text—1395
LMArena Creative Writing—1378
EQ-Bench Creative Writing—2125
LMArena Multi-Turn—1412

Frequently asked questions

Is GPT-5.2 Pro better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 52.3 on the Noometry Index.

Which is cheaper, GPT-5.2 Pro or GPT-6 Sol?

GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5.2 Pro lists at $21 and $168.

Which has the bigger context window?

GPT-6 Sol does, with 1.05M tokens against 400K.

How many benchmarks do GPT-5.2 Pro and GPT-6 Sol share?

6 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper