Noometry

Model comparison

Gemini 3.8 Flash vs Llama-3.3-70B-Instruct

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 9.7× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

Last verified . 25 shared benchmarks.

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 9 categories and Llama-3.3-70B-Instruct in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 14.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Gemini 3.8 Flash and 5.1% for Llama-3.3-70B-Instruct.
  • Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
  • Gemini 3.8 Flash accepts more context: 1.05M tokens versus 128K.
  • Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.

Side by side

Gemini 3.8 FlashLlama-3.3-70B-Instruct
ProviderGoogleMeta
Noometry Index61.830.6
Released2026-09-022024-12-06
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$0.75$0.10
Output $ / M tokens$3.75$0.32
Results tracked5043

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

Category by category

Coding Gemini 3.8 Flash leads

Gemini 3.8 Flash: 59.2 (#15), Llama-3.3-70B-Instruct: 31.0 (#290)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
SciCode56.6%26%
WeirdML84.8%14.4%
LMArena Coding15101268
DeepSWE73.8%—
FrontierCode41.2%—
CursorBench39.6%—
LMArena WebDev1584—
FrontierSWE19.6%—
BigCodeBench Instruct—46.9%
LiveBench Coding—36.6%
BigCodeBench Complete—57.5%
ALE-Bench1,270—

Agentic & Tool Use Gemini 3.8 Flash leads

Gemini 3.8 Flash: 41.8 (#21), Llama-3.3-70B-Instruct: 25.8 (#105)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
APEX-Agents64.3%—
Berkeley Function Calling Leaderboard—31.9%
Remote Labor Index5.8%—
BALROG—23%
GDP.pdf23.4%—
Vending-Bench 25,094—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 76.9 (#5), Llama-3.3-70B-Instruct: 14.1 (#327)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
CritPt18.3%0%
LMArena Hard Prompts15081257
DTBench95.7%59.5%
LMCA52.9%17.5%
Epoch Capabilities Index156.71127.33
ARC-AGI-289.2%—
SimpleBench—19.9%
NYT Connections (extended)97.4%—
ARC-AGI-198.5%—
Chess Puzzles61%—
LiveBench Reasoning—50.8%
Mystery Game Puzzles47%—
LiveBench Data Analysis—49.5%
Surface Evolver Bench76.9%—
ForecastBench—58.6
LiveBench—50.2%

Math Gemini 3.8 Flash leads

Gemini 3.8 Flash: 65.3 (#28), Llama-3.3-70B-Instruct: 15.3 (#298)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
OTIS Mock AIME 2024-202598.9%5.1%
LMArena Math15281267
FrontierMath (Tiers 1-3)68.4%—
FrontierMath Tier 422%—
ProofBench48%—
LiveBench Math—42.2%
MATH Level 5—41.6%

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.8 (#2), Llama-3.3-70B-Instruct: 30.6 (#226)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
GPQA Diamond95.4%47.4%
LMArena Expert15241225
Humanity's Last Exam44.5%—
SimpleQA Verified69.7%—
Confabulations—22.8%
Vectara Hallucination Rate—4.1%
MMLU—86.3%

Multimodal Not comparable

Gemini 3.8 Flash: 40.7 (#45), Llama-3.3-70B-Instruct: —

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
LMArena Vision1314—
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—

Multilingual Gemini 3.8 Flash leads

Gemini 3.8 Flash: 58.0 (#5), Llama-3.3-70B-Instruct: 39.9 (#220)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
LMArena Non-English14911236
LMArena Chinese15541217
LMArena French14981281
LMArena German14931251
LMArena Japanese15021150
LMArena Korean14591143
LMArena Russian15151252
LMArena Spanish14851270

Instruction Following Gemini 3.8 Flash leads

Gemini 3.8 Flash: 78.0 (#13), Llama-3.3-70B-Instruct: 71.1 (#157)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
LMArena Instruction Following14901242
LiveBench Instruction Following—82.7%

Long Context Gemini 3.8 Flash leads

Gemini 3.8 Flash: 46.3 (#24), Llama-3.3-70B-Instruct: 26.4 (#295)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
LMArena Longer Query15081256
Fiction.LiveBench—33.3%

Writing & Preference Gemini 3.8 Flash leads

Gemini 3.8 Flash: 72.2 (#15), Llama-3.3-70B-Instruct: 47.6 (#207)

BenchmarkGemini 3.8 FlashLlama-3.3-70B-Instruct
LMArena Text14991274
LMArena Creative Writing14921250
LMArena Multi-Turn15011280
EQ-Bench Creative Writing1748—
LiveBench Language—39.2%

Frequently asked questions

Is Gemini 3.8 Flash better than Llama-3.3-70B-Instruct?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 9.7× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.8 Flash or Llama-3.3-70B-Instruct?

Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

Is Gemini 3.8 Flash or Llama-3.3-70B-Instruct better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 31.0 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3.8 Flash and Llama-3.3-70B-Instruct share?

25 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Llama-3.3-70B-Instruct has 43.

Related comparisons

Go deeper