Noometry

Model comparison

Gemini 3.7 Flash vs Llama 3-8B

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 25.5 on the Noometry Index.

Last verified . 22 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #14 Confirmed

Llama 3-8B Meta

25.5

Rank #344 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.7 Flash leads 69.7 to 7.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Gemini 3.7 Flash and 1.9% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.7 FlashLlama 3-8B
ProviderGoogleMeta
Noometry Index59.825.5
Released2026-08-132024-04-18
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked4434

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

Category by category

Coding Gemini 3.7 Flash leads

Gemini 3.7 Flash: 56.2 (#22), Llama 3-8B: 31.0 (#289)

BenchmarkGemini 3.7 FlashLlama 3-8B
LMArena Coding14971152
DeepSWE65.5%—
FrontierCode43.6%—
LMArena WebDev1592—
FrontierSWE20.3%—
SciCode59.8%—
BigCodeBench Instruct—31.9%
BigCodeBench Complete—36.9%
ALE-Bench904.3—
HumanEval+—56.7%
MBPP+—54.8%

Agentic & Tool Use Not comparable

Gemini 3.7 Flash: 42.1 (#19), Llama 3-8B: —

BenchmarkGemini 3.7 FlashLlama 3-8B
APEX-Agents67.8%—
Remote Labor Index5%—
GDP.pdf23.8%—

Reasoning Gemini 3.7 Flash leads

Gemini 3.7 Flash: 70.0 (#15), Llama 3-8B: 14.3 (#326)

BenchmarkGemini 3.7 FlashLlama 3-8B
Chess Puzzles47%0%
LMArena Hard Prompts14941133
DTBench96.8%43.9%
Epoch Capabilities Index157.27116.45
ARC-AGI-284.6%—
NYT Connections (extended)94%—
ARC-AGI-195.5%—
CritPt14.3%—
Mystery Game Puzzles37%—
LMCA50.4%—
Adversarial NLI—57.3%
ForecastBench—58.6
WinoGrande—75.7%

Math Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.6 (#23), Llama 3-8B: 8.8 (#323)

BenchmarkGemini 3.7 FlashLlama 3-8B
OTIS Mock AIME 2024-202597.2%1.9%
LMArena Math15071151
FrontierMath (Tiers 1-3)71.6%—
FrontierMath Tier 436.6%—
ProofBench58%—
MATH Level 5—6.1%

Knowledge Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.7 (#5), Llama 3-8B: 7.8 (#308)

BenchmarkGemini 3.7 FlashLlama 3-8B
GPQA Diamond94.8%26.1%
LMArena Expert15081113
SimpleQA Verified69.2%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multimodal Not comparable

Gemini 3.7 Flash: 37.3 (#73), Llama 3-8B: —

BenchmarkGemini 3.7 FlashLlama 3-8B
LMArena Vision1316—
Furniture Assembly26.7%—

Multilingual Gemini 3.7 Flash leads

Gemini 3.7 Flash: 57.6 (#7), Llama 3-8B: 30.8 (#261)

BenchmarkGemini 3.7 FlashLlama 3-8B
LMArena Non-English14841098
LMArena Chinese15481076
LMArena French15051159
LMArena German14981104
LMArena Japanese1512967
LMArena Korean14831004
LMArena Russian15161109
LMArena Spanish15031173

Instruction Following Gemini 3.7 Flash leads

Gemini 3.7 Flash: 77.7 (#15), Llama 3-8B: 58.4 (#260)

BenchmarkGemini 3.7 FlashLlama 3-8B
LMArena Instruction Following14831127

Long Context Gemini 3.7 Flash leads

Gemini 3.7 Flash: 45.7 (#30), Llama 3-8B: 34.2 (#251)

BenchmarkGemini 3.7 FlashLlama 3-8B
LMArena Longer Query14921128

Writing & Preference Gemini 3.7 Flash leads

Gemini 3.7 Flash: 71.2 (#20), Llama 3-8B: 37.5 (#256)

BenchmarkGemini 3.7 FlashLlama 3-8B
LMArena Text14861166
LMArena Creative Writing14901150
LMArena Multi-Turn14891152
EQ-Bench Creative Writing1723—

Frequently asked questions

Is Gemini 3.7 Flash better than Llama 3-8B?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 25.5 on the Noometry Index.

Is Gemini 3.7 Flash or Llama 3-8B better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 31.0 in the Noometry coding category.

How many benchmarks do Gemini 3.7 Flash and Llama 3-8B share?

22 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper