Noometry

Model comparison

GPT-6.1 Sol vs Llama 3-70B

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 28.8 on the Noometry Index.

Last verified . 15 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Summary

  • They share 15 benchmarks with published results for both. GPT-6.1 Sol scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 12.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6.1 Sol and 4.3% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 SolLlama 3-70B
ProviderOpenAIMeta
Noometry Index65.628.8
Released2026-09-292024-04-18
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3431

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 3-70B: 35.8 (#218)

BenchmarkGPT-6.1 SolLlama 3-70B
LMArena Coding14871206
DeepSWE75.2%—
FrontierCode50.2%—
LMArena WebDev1755—
SciCode55.8%—
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use GPT-6.1 Sol leads

GPT-6.1 Sol: 39.6 (#26), Llama 3-70B: 21.1 (#139)

BenchmarkGPT-6.1 SolLlama 3-70B
APEX-Agents60%—
Cybench—5%
GDP.pdf32%—

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Llama 3-70B: 18.0 (#288)

BenchmarkGPT-6.1 SolLlama 3-70B
LMArena Hard Prompts14661195
Epoch Capabilities Index166.09122.93
ARC-AGI-294.2%—
Kagi LLM Benchmark—35.1%
NYT Connections (extended)95.5%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles61%—
EBR-Bench54.3%—
Mystery Game Puzzles80%—
DTBench—54.2%
ForecastBench—57.1
WinoGrande—83.5%

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Llama 3-70B: 12.8 (#305)

BenchmarkGPT-6.1 SolLlama 3-70B
OTIS Mock AIME 2024-2025100%4.3%
LMArena Math14641218
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
ProofBench99%—
MATH Level 5—22.6%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Llama 3-70B: 20.8 (#277)

BenchmarkGPT-6.1 SolLlama 3-70B
GPQA Diamond95.4%40.6%
LMArena Expert15021149
SimpleQA Verified73.9%—
MMLU—79.3%

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Llama 3-70B: —

BenchmarkGPT-6.1 SolLlama 3-70B
LMArena Vision1288—
Furniture Assembly80%—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Llama 3-70B: 33.6 (#251)

BenchmarkGPT-6.1 SolLlama 3-70B
LMArena Non-English14381142
LMArena Chinese14771114
LMArena Russian14551159
LMArena French—1232
LMArena German—1169
LMArena Japanese—1017
LMArena Korean—1017
LMArena Spanish—1241

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), Llama 3-70B: 62.5 (#238)

BenchmarkGPT-6.1 SolLlama 3-70B
LMArena Instruction Following14681194

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), Llama 3-70B: 35.6 (#240)

BenchmarkGPT-6.1 SolLlama 3-70B
LMArena Longer Query14651174

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Llama 3-70B: 42.8 (#231)

BenchmarkGPT-6.1 SolLlama 3-70B
LMArena Text14471221
LMArena Creative Writing14321210
LMArena Multi-Turn14491223

Frequently asked questions

Is GPT-6.1 Sol better than Llama 3-70B?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 28.8 on the Noometry Index.

Is GPT-6.1 Sol or Llama 3-70B better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 35.8 in the Noometry coding category.

How many benchmarks do GPT-6.1 Sol and Llama 3-70B share?

15 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper