Noometry

Model comparison

GPT-6.1 Sol vs Llama 3-8B

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 25.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Llama 3-8B Meta

25.5

Rank #344 Confirmed

Summary

  • They share 16 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Llama 3-8B 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 8.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6.1 Sol and 1.9% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 SolLlama 3-8B
ProviderOpenAIMeta
Noometry Index65.625.5
Released2026-09-292024-04-18
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3434

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), Llama 3-8B: 31.0 (#289)

BenchmarkGPT-6.1 SolLlama 3-8B
LMArena Coding14871152
DeepSWE75.2%—
FrontierCode50.2%—
LMArena WebDev1755—
SciCode55.8%—
BigCodeBench Instruct—31.9%
BigCodeBench Complete—36.9%
HumanEval+—56.7%
MBPP+—54.8%

Agentic & Tool Use Not comparable

GPT-6.1 Sol: 39.6 (#26), Llama 3-8B: —

BenchmarkGPT-6.1 SolLlama 3-8B
APEX-Agents60%—
GDP.pdf32%—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Llama 3-8B: 14.3 (#326)

BenchmarkGPT-6.1 SolLlama 3-8B
Chess Puzzles61%0%
LMArena Hard Prompts14661133
Epoch Capabilities Index166.09116.45
ARC-AGI-294.2%—
NYT Connections (extended)95.5%—
ARC-AGI-198.5%—
CritPt31.7%—
EBR-Bench54.3%—
Mystery Game Puzzles80%—
DTBench—43.9%
Adversarial NLI—57.3%
ForecastBench—58.6
WinoGrande—75.7%

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Llama 3-8B: 8.8 (#323)

BenchmarkGPT-6.1 SolLlama 3-8B
OTIS Mock AIME 2024-2025100%1.9%
LMArena Math14641151
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
ProofBench99%—
MATH Level 5—6.1%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Llama 3-8B: 7.8 (#308)

BenchmarkGPT-6.1 SolLlama 3-8B
GPQA Diamond95.4%26.1%
LMArena Expert15021113
SimpleQA Verified73.9%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Llama 3-8B: —

BenchmarkGPT-6.1 SolLlama 3-8B
LMArena Vision1288—
Furniture Assembly80%—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Llama 3-8B: 30.8 (#261)

BenchmarkGPT-6.1 SolLlama 3-8B
LMArena Non-English14381098
LMArena Chinese14771076
LMArena Russian14551109
LMArena French—1159
LMArena German—1104
LMArena Japanese—967
LMArena Korean—1004
LMArena Spanish—1173

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), Llama 3-8B: 58.4 (#260)

BenchmarkGPT-6.1 SolLlama 3-8B
LMArena Instruction Following14681127

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), Llama 3-8B: 34.2 (#251)

BenchmarkGPT-6.1 SolLlama 3-8B
LMArena Longer Query14651128

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Llama 3-8B: 37.5 (#256)

BenchmarkGPT-6.1 SolLlama 3-8B
LMArena Text14471166
LMArena Creative Writing14321150
LMArena Multi-Turn14491152

Frequently asked questions

Is GPT-6.1 Sol better than Llama 3-8B?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 25.5 on the Noometry Index.

Is GPT-6.1 Sol or Llama 3-8B better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 31.0 in the Noometry coding category.

How many benchmarks do GPT-6.1 Sol and Llama 3-8B share?

16 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper