Noometry

Model comparison

GPT-6.1 Sol vs GPT-6 Sol

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 61.8 on the Noometry Index.

Last verified . 33 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 33 benchmarks with published results for both. GPT-6.1 Sol scores higher in 9 categories and GPT-6 Sol in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-6 Sol leads 71.9 to 63.6.
  • The biggest single-benchmark swing is Mystery Game Puzzles: 80% for GPT-6.1 Sol and 56% for GPT-6 Sol.
  • Both cost about the same: $2 input and $10 output per million tokens.

Side by side

GPT-6.1 SolGPT-6 Sol
ProviderOpenAIOpenAI
Noometry Index65.661.8
Released2026-09-292026-09-22
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output128K128K
Input $ / M tokens$2$2
Output $ / M tokens$10$10
Results tracked3445

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), GPT-6 Sol: 60.1 (#11)

BenchmarkGPT-6.1 SolGPT-6 Sol
DeepSWE75.2%68.8%
FrontierCode50.2%49.3%
LMArena WebDev17551688
SciCode55.8%57.6%
LMArena Coding14871447
ALE-Bench—2,462

Agentic & Tool Use GPT-6.1 Sol leads

GPT-6.1 Sol: 39.6 (#26), GPT-6 Sol: 37.2 (#36)

BenchmarkGPT-6.1 SolGPT-6 Sol
APEX-Agents60%54.3%
GDP.pdf32%26.4%
Vending-Bench 2—14,428

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), GPT-6 Sol: 74.0 (#9)

BenchmarkGPT-6.1 SolGPT-6 Sol
ARC-AGI-294.2%89.6%
NYT Connections (extended)95.5%90.1%
ARC-AGI-198.5%95.5%
CritPt31.7%30.9%
EBR-Bench54.3%53.3%
LMArena Hard Prompts14661418
Mystery Game Puzzles80%56%
Epoch Capabilities Index166.09162.72
Chess Puzzles61%—
DTBench—97.3%
LMCA—59.1%

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), GPT-6 Sol: 87.2 (#7)

BenchmarkGPT-6.1 SolGPT-6 Sol
FrontierMath (Tiers 1-3)93.7%89.8%
FrontierMath Tier 4100%90%
OTIS Mock AIME 2024-2025100%100%
ProofBench99%83%
LMArena Math14641402

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), GPT-6 Sol: 64.8 (#15)

BenchmarkGPT-6.1 SolGPT-6 Sol
GPQA Diamond95.4%94.3%
SimpleQA Verified73.9%60.7%
LMArena Expert15021439
Vectara Hallucination Rate—6.5%

Multimodal GPT-6.1 Sol leads

GPT-6.1 Sol: 52.7 (#5), GPT-6 Sol: 47.6 (#10)

BenchmarkGPT-6.1 SolGPT-6 Sol
LMArena Vision12881245
Furniture Assembly80%58.3%
Blueprint-Bench 2—36.9%

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), GPT-6 Sol: 50.5 (#118)

BenchmarkGPT-6.1 SolGPT-6 Sol
LMArena Non-English14381385
LMArena Chinese14771405
LMArena Russian14551401
LMArena French—1410
LMArena German—1390
LMArena Japanese—1385
LMArena Korean—1341
LMArena Spanish—1384

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), GPT-6 Sol: 74.5 (#94)

BenchmarkGPT-6.1 SolGPT-6 Sol
LMArena Instruction Following14681412

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), GPT-6 Sol: 43.1 (#108)

BenchmarkGPT-6.1 SolGPT-6 Sol
LMArena Longer Query14651411

Writing & Preference GPT-6 Sol leads

GPT-6.1 Sol: 63.6 (#63), GPT-6 Sol: 71.9 (#18)

BenchmarkGPT-6.1 SolGPT-6 Sol
LMArena Text14471395
LMArena Creative Writing14321378
LMArena Multi-Turn14491412
EQ-Bench Creative Writing—2125

Frequently asked questions

Is GPT-6.1 Sol better than GPT-6 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 61.8 on the Noometry Index.

Which is cheaper, GPT-6.1 Sol or GPT-6 Sol?

GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

Is GPT-6.1 Sol or GPT-6 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 60.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do GPT-6.1 Sol and GPT-6 Sol share?

33 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper