Noometry

Model comparison

GPT-6.1 Sol vs Granite 3.1 2b Instruct

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 33.2 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Granite 3.1 2b Instruct IBM

33.2

Rank #247 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Granite 3.1 2b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 33.1.
  • Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 SolGranite 3.1 2b Instruct
ProviderOpenAIIBM
Noometry Index65.633.2
Released2026-09-29—
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3412

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), Granite 3.1 2b Instruct: 33.4 (#257)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Coding14871149
DeepSWE75.2%—
FrontierCode50.2%—
LMArena WebDev1755—
SciCode55.8%—

Agentic & Tool Use Not comparable

GPT-6.1 Sol: 39.6 (#26), Granite 3.1 2b Instruct: —

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
APEX-Agents60%—
GDP.pdf32%—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Granite 3.1 2b Instruct: 22.0 (#209)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Hard Prompts14661138
ARC-AGI-294.2%—
NYT Connections (extended)95.5%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles61%—
EBR-Bench54.3%—
Mystery Game Puzzles80%—
Epoch Capabilities Index166.09—

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Granite 3.1 2b Instruct: 33.1 (#206)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Math14641159
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Granite 3.1 2b Instruct: 30.8 (#224)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Expert15021131
GPQA Diamond95.4%—
SimpleQA Verified73.9%—

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Granite 3.1 2b Instruct: —

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Vision1288—
Furniture Assembly80%—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Granite 3.1 2b Instruct: 29.1 (#269)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Non-English14381068
LMArena Chinese14771139
LMArena Russian14551063

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), Granite 3.1 2b Instruct: 57.7 (#264)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Instruction Following14681116

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), Granite 3.1 2b Instruct: 35.0 (#244)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Longer Query14651155

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Granite 3.1 2b Instruct: 34.1 (#274)

BenchmarkGPT-6.1 SolGranite 3.1 2b Instruct
LMArena Text14471127
LMArena Creative Writing14321116
LMArena Multi-Turn14491099

Frequently asked questions

Is GPT-6.1 Sol better than Granite 3.1 2b Instruct?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 33.2 on the Noometry Index.

Is GPT-6.1 Sol or Granite 3.1 2b Instruct better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 33.4 in the Noometry coding category.

How many benchmarks do GPT-6.1 Sol and Granite 3.1 2b Instruct share?

12 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Granite 3.1 2b Instruct has 12.

Related comparisons

Go deeper