Noometry

Model comparison

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

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 22× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified . 39 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Gemini 2.5 Pro 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 long context, where Gemini 2.5 Pro leads 59.8 to 26.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.7% for Gemini 2.5 Pro 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 $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro 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 ProLlama-3.3-70B-Instruct
ProviderGoogleMeta
Noometry Index45.030.6
Released2025-03-252024-12-06
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$1.25$0.10
Output $ / M tokens$10$0.32
Results tracked7843

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

Category by category

Coding Gemini 2.5 Pro leads

Gemini 2.5 Pro: 42.4 (#101), Llama-3.3-70B-Instruct: 31.0 (#290)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
SciCode42.8%26%
WeirdML54%14.4%
LiveBench Coding85.9%36.6%
LMArena Coding14521268
SWE-bench Verified57.6%—
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
LMArena WebDev1227—
GSO3.9%—
BigCodeBench Instruct—46.9%
BigCodeBench Complete—57.5%
CadEval64%—
ALE-Bench785.52—
AlgoTune1.51—

Agentic & Tool Use Gemini 2.5 Pro leads

Gemini 2.5 Pro: 29.2 (#88), Llama-3.3-70B-Instruct: 25.8 (#105)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
BALROG43.3%23%
Terminal-Bench32.6%—
Berkeley Function Calling Leaderboard—31.9%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
LMArena Search1142—
METR Time Horizons55.4%—
Vending-Bench 2573.64—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#99), Llama-3.3-70B-Instruct: 14.1 (#327)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
SimpleBench62.4%19.9%
CritPt2%0%
LiveBench Reasoning89.8%50.8%
LMArena Hard Prompts14551257
DTBench82.4%59.5%
LiveBench Data Analysis79.9%49.5%
LMCA34.8%17.5%
Epoch Capabilities Index145.32127.33
ForecastBench61.358.6
LiveBench82.3%50.2%
ARC-AGI-24.9%—
Kagi LLM Benchmark70.3%—
ARC-AGI-141%—
Chess Puzzles20%—
EnigmaEval5.6%—

Math Gemini 2.5 Pro leads

Gemini 2.5 Pro: 32.5 (#213), Llama-3.3-70B-Instruct: 15.3 (#298)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
OTIS Mock AIME 2024-202584.7%5.1%
LiveBench Math90.2%42.2%
LMArena Math14501267
MATH Level 595.9%41.6%
FrontierMath (Tiers 1-3)24.6%—
FrontierMath Tier 40%—
Omni-MATH41.6%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), Llama-3.3-70B-Instruct: 30.6 (#226)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
GPQA Diamond85.3%47.4%
Confabulations10.6%22.8%
Vectara Hallucination Rate7%4.1%
LMArena Expert14521225
Humanity's Last Exam21.6%—
MMLU-Pro86.3%—
GPQA (HELM)74.9%—
MMLU—86.3%

Multimodal Not comparable

Gemini 2.5 Pro: 45.2 (#18), Llama-3.3-70B-Instruct: —

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
LMArena Vision1263—
GeoBench86%—
VPCT48%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), Llama-3.3-70B-Instruct: 39.9 (#220)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
LMArena Non-English14511236
LMArena Chinese15071217
LMArena French14721281
LMArena German14871251
LMArena Japanese14611150
LMArena Korean14341143
LMArena Russian14611252
LMArena Spanish14731270

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.0 (#75), Llama-3.3-70B-Instruct: 71.1 (#157)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
LiveBench Instruction Following80.6%82.7%
LMArena Instruction Following14371242
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Llama-3.3-70B-Instruct: 26.4 (#295)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
Fiction.LiveBench91.7%33.3%
LMArena Longer Query14491256

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), Llama-3.3-70B-Instruct: 47.6 (#207)

BenchmarkGemini 2.5 ProLlama-3.3-70B-Instruct
LMArena Text14581274
LMArena Creative Writing14541250
LMArena Multi-Turn14531280
LiveBench Language67.8%39.2%
Short-Story Creative Writing83.8%—
EQ-Bench Creative Writing1421—
WildBench85.7%—

Frequently asked questions

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

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 22× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Pro 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 Pro lists at $1.25 and $10.

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

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 31.0 in the Noometry coding category.

Which has the bigger context window?

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

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

39 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Llama-3.3-70B-Instruct has 43.

Related comparisons

Go deeper