Noometry

Model comparison

Gemini 3.7 Flash vs Llama 2-70B

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 24.4 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #14 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 8 categories and Llama 2-70B 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 7.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Gemini 3.7 Flash and 0% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.7 FlashLlama 2-70B
ProviderGoogleMeta
Noometry Index59.824.4
Released2026-08-132023-07-18
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked4435

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 2-70B: 31.4 (#286)

BenchmarkGemini 3.7 FlashLlama 2-70B
LMArena Coding14971079
DeepSWE65.5%—
FrontierCode43.6%—
LMArena WebDev1592—
FrontierSWE20.3%—
SciCode59.8%—
ALE-Bench904.3—

Agentic & Tool Use Not comparable

Gemini 3.7 Flash: 42.1 (#19), Llama 2-70B: —

BenchmarkGemini 3.7 FlashLlama 2-70B
APEX-Agents67.8%—
Remote Labor Index5%—
GDP.pdf23.8%—

Reasoning Gemini 3.7 Flash leads

Gemini 3.7 Flash: 70.0 (#15), Llama 2-70B: 14.4 (#325)

BenchmarkGemini 3.7 FlashLlama 2-70B
LMArena Hard Prompts14941073
DTBench96.8%41.6%
Epoch Capabilities Index157.27113.79
ARC-AGI-284.6%—
NYT Connections (extended)94%—
ARC-AGI-195.5%—
CritPt14.3%—
Chess Puzzles47%—
Mystery Game Puzzles37%—
LMCA50.4%—
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
PIQA—82.8%
WinoGrande—80.2%

Math Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.6 (#23), Llama 2-70B: 8.1 (#326)

BenchmarkGemini 3.7 FlashLlama 2-70B
OTIS Mock AIME 2024-202597.2%0%
LMArena Math15071091
FrontierMath (Tiers 1-3)71.6%—
FrontierMath Tier 436.6%—
ProofBench58%—
MATH Level 5—3.3%
GSM8K—69.6%

Knowledge Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.7 (#5), Llama 2-70B: 7.4 (#310)

BenchmarkGemini 3.7 FlashLlama 2-70B
GPQA Diamond94.8%26.3%
LMArena Expert15081039
SimpleQA Verified69.2%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
MMLU—69.9%
OpenBookQA—60.2%
TriviaQA—87.6%

Multimodal Not comparable

Gemini 3.7 Flash: 37.3 (#73), Llama 2-70B: —

BenchmarkGemini 3.7 FlashLlama 2-70B
LMArena Vision1316—
Furniture Assembly26.7%—

Multilingual Gemini 3.7 Flash leads

Gemini 3.7 Flash: 57.6 (#7), Llama 2-70B: 27.7 (#274)

BenchmarkGemini 3.7 FlashLlama 2-70B
LMArena Non-English14841045
LMArena Chinese1548995
LMArena French15051090
LMArena German14981041
LMArena Japanese1512927
LMArena Korean1483964
LMArena Russian15161083
LMArena Spanish15031143

Instruction Following Gemini 3.7 Flash leads

Gemini 3.7 Flash: 77.7 (#15), Llama 2-70B: 54.9 (#278)

BenchmarkGemini 3.7 FlashLlama 2-70B
LMArena Instruction Following14831071

Long Context Gemini 3.7 Flash leads

Gemini 3.7 Flash: 45.7 (#30), Llama 2-70B: 32.3 (#270)

BenchmarkGemini 3.7 FlashLlama 2-70B
LMArena Longer Query14921062

Writing & Preference Gemini 3.7 Flash leads

Gemini 3.7 Flash: 71.2 (#20), Llama 2-70B: 32.3 (#279)

BenchmarkGemini 3.7 FlashLlama 2-70B
LMArena Text14861115
LMArena Creative Writing14901075
LMArena Multi-Turn14891088
EQ-Bench Creative Writing1723—

Frequently asked questions

Is Gemini 3.7 Flash better than Llama 2-70B?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 24.4 on the Noometry Index.

Is Gemini 3.7 Flash or Llama 2-70B better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 31.4 in the Noometry coding category.

How many benchmarks do Gemini 3.7 Flash and Llama 2-70B share?

21 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper