Noometry

Model comparison

Gemini 3 Flash Preview vs Llama-3.3-70B-Instruct

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 7.3× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Gemini 3 Flash Preview 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 math, where Gemini 3 Flash Preview leads 51.7 to 15.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview 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 $0.50 / $3 for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview 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 Flash PreviewLlama-3.3-70B-Instruct
ProviderGoogleMeta
Noometry Index52.330.6
Released2025-12-172024-12-06
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$0.50$0.10
Output $ / M tokens$3$0.32
Results tracked5943

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

Category by category

Coding Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 50.9 (#42), Llama-3.3-70B-Instruct: 31.0 (#290)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
WeirdML61.6%14.4%
LMArena Coding14601268
SWE-bench Verified75.4%—
SWE-bench Verified (bash only)75.8%—
LMArena WebDev1439—
SWE-bench Multilingual72.7%—
SciCode—26%
GSO9.8%—
BigCodeBench Instruct—46.9%
LiveBench Coding—36.6%
BigCodeBench Complete—57.5%
ALE-Bench1,367—

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.7 (#29), Llama-3.3-70B-Instruct: 25.8 (#105)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
BALROG48.1%23%
Terminal-Bench64.3%—
Berkeley Function Calling Leaderboard—31.9%
τ²-bench Airline82.5%—
τ²-bench Banking27.3%—
τ²-bench Retail76.8%—
τ²-bench Telecom91.2%—
DeepResearch Bench49.8%—
GDP.pdf10%—
LMArena Search1198—
Vending-Bench 23,635—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#37), Llama-3.3-70B-Instruct: 14.1 (#327)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
SimpleBench61.1%19.9%
LMArena Hard Prompts14651257
DTBench89.1%59.5%
LMCA43.1%17.5%
Epoch Capabilities Index151.8127.33
ForecastBench58.558.6
ARC-AGI-233.6%—
NYT Connections (extended)83.1%—
ARC-AGI-184.7%—
CritPt—0%
Chess Puzzles40%—
LiveBench Reasoning—50.8%
Mystery Game Puzzles26%—
LiveBench Data Analysis—49.5%
LiveBench—50.2%

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.7 (#55), Llama-3.3-70B-Instruct: 15.3 (#298)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
OTIS Mock AIME 2024-202595.6%5.1%
LMArena Math14731267
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 417.1%—
MathArena Final-Answer Competitions67.6%—
ProofBench15%—
LiveBench Math—42.2%
MATH Level 5—41.6%
FrontierMath (Feb 2025 set)35.6%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#33), Llama-3.3-70B-Instruct: 30.6 (#226)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
GPQA Diamond89.4%47.4%
Vectara Hallucination Rate13.5%4.1%
LMArena Expert14621225
SimpleQA Verified66.8%—
Confabulations—22.8%
MMLU—86.3%

Multimodal Not comparable

Gemini 3 Flash Preview: 45.5 (#16), Llama-3.3-70B-Instruct: —

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
LMArena Vision1285—
GeoBench88%—
VPCT72.6%—
Blueprint-Bench 20%—
LMArena Document1413—

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.7 (#27), Llama-3.3-70B-Instruct: 39.9 (#220)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
LMArena Non-English14581236
LMArena Chinese15111217
LMArena French14771281
LMArena German14971251
LMArena Japanese14891150
LMArena Korean14431143
LMArena Russian14801252
LMArena Spanish14691270

Instruction Following Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 75.7 (#56), Llama-3.3-70B-Instruct: 71.1 (#157)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
LMArena Instruction Following14371242
LiveBench Instruction Following—82.7%

Long Context Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 44.4 (#67), Llama-3.3-70B-Instruct: 26.4 (#295)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
LMArena Longer Query14521256
Fiction.LiveBench—33.3%

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.5 (#45), Llama-3.3-70B-Instruct: 47.6 (#207)

BenchmarkGemini 3 Flash PreviewLlama-3.3-70B-Instruct
LMArena Text14661274
LMArena Creative Writing14571250
LMArena Multi-Turn14711280
LiveBench Language—39.2%

Frequently asked questions

Is Gemini 3 Flash Preview better than Llama-3.3-70B-Instruct?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 7.3× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3 Flash Preview 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 Flash Preview lists at $0.50 and $3.

Is Gemini 3 Flash Preview or Llama-3.3-70B-Instruct better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 31.0 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3 Flash Preview and Llama-3.3-70B-Instruct share?

27 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Llama-3.3-70B-Instruct has 43.

Related comparisons

Go deeper