Noometry

Model comparison

Gemini 2.5 Flash vs Llama-3.3-70B-Instruct

Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 5.5× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Gemini 2.5 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 math, where Gemini 2.5 Flash leads 39.9 to 15.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 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 $0.30 / $2.50 for Gemini 2.5 Flash.
  • Gemini 2.5 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 2.5 FlashLlama-3.3-70B-Instruct
ProviderGoogleMeta
Noometry Index39.330.6
Released2025-04-172024-12-06
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$0.30$0.10
Output $ / M tokens$2.50$0.32
Results tracked5443

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

Category by category

Coding Gemini 2.5 Flash leads

Gemini 2.5 Flash: 35.8 (#220), Llama-3.3-70B-Instruct: 31.0 (#290)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
WeirdML41.9%14.4%
LMArena Coding14241268
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
SciCode—26%
BigCodeBench Instruct—46.9%
LiveBench Coding—36.6%
BigCodeBench Complete—57.5%
ALE-Bench661.88—

Agentic & Tool Use Gemini 2.5 Flash leads

Gemini 2.5 Flash: 30.8 (#74), Llama-3.3-70B-Instruct: 25.8 (#105)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
Berkeley Function Calling Leaderboard56.2%31.9%
BALROG33.5%23%
Terminal-Bench17.1%—
TheAgentCompany41.1%—
Vending-Bench 2548.84—

Reasoning Gemini 2.5 Flash leads

Gemini 2.5 Flash: 18.1 (#286), Llama-3.3-70B-Instruct: 14.1 (#327)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
SimpleBench41.2%19.9%
CritPt1.1%0%
LMArena Hard Prompts14221257
DTBench76.5%59.5%
LMCA27.5%17.5%
Epoch Capabilities Index143.03127.33
ForecastBench60.658.6
ARC-AGI-22.5%—
Kagi LLM Benchmark56.8%—
ARC-AGI-133.3%—
EnigmaEval2.7%—
LiveBench Reasoning—50.8%
LiveBench Data Analysis—49.5%
LiveBench—50.2%

Math Gemini 2.5 Flash leads

Gemini 2.5 Flash: 39.9 (#98), Llama-3.3-70B-Instruct: 15.3 (#298)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
OTIS Mock AIME 2024-202573.1%5.1%
LMArena Math14151267
Omni-MATH38.5%—
LiveBench Math—42.2%
MATH Level 5—41.6%
FrontierMath (Feb 2025 set)4.8%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 2.5 Flash leads

Gemini 2.5 Flash: 36.4 (#168), Llama-3.3-70B-Instruct: 30.6 (#226)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
Confabulations16.8%22.8%
Vectara Hallucination Rate7.8%4.1%
LMArena Expert14261225
GPQA Diamond—47.4%
Humanity's Last Exam12.1%—
MMLU-Pro63.9%—
GPQA (HELM)39%—
MMLU—86.3%

Multimodal Not comparable

Gemini 2.5 Flash: 41.8 (#32), Llama-3.3-70B-Instruct: —

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
LMArena Vision1253—
GeoBench76%—
VPCT46.2%—
SpatialViz-Bench36.9%—

Multilingual Gemini 2.5 Flash leads

Gemini 2.5 Flash: 52.3 (#88), Llama-3.3-70B-Instruct: 39.9 (#220)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
LMArena Non-English14091236
LMArena Chinese14501217
LMArena French14331281
LMArena German14181251
LMArena Japanese14051150
LMArena Korean13851143
LMArena Russian14151252
LMArena Spanish14211270

Instruction Following Gemini 2.5 Flash leads

Gemini 2.5 Flash: 75.7 (#54), Llama-3.3-70B-Instruct: 71.1 (#157)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
LMArena Instruction Following14051242
LiveBench Instruction Following—82.7%
IFEval89.8%—

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Llama-3.3-70B-Instruct: 26.4 (#295)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
Fiction.LiveBench77.8%33.3%
LMArena Longer Query14191256

Writing & Preference Gemini 2.5 Flash leads

Gemini 2.5 Flash: 53.8 (#157), Llama-3.3-70B-Instruct: 47.6 (#207)

BenchmarkGemini 2.5 FlashLlama-3.3-70B-Instruct
LMArena Text14171274
LMArena Creative Writing14001250
LMArena Multi-Turn14081280
Short-Story Creative Writing76.5%—
EQ-Bench Creative Writing1137—
WildBench81.7%—
LiveBench Language—39.2%

Frequently asked questions

Is Gemini 2.5 Flash better than Llama-3.3-70B-Instruct?

Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 5.5× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 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 2.5 Flash lists at $0.30 and $2.50.

Is Gemini 2.5 Flash or Llama-3.3-70B-Instruct better for coding?

Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 31.0 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 2.5 Flash and Llama-3.3-70B-Instruct share?

30 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Llama-3.3-70B-Instruct has 43.

Related comparisons

Go deeper