Noometry

Model comparison

Gemini 3.1 Pro Preview vs Llama-3.3-70B-Instruct

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 29× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 29 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #20 Confirmed

Llama-3.3-70B-Instruct Meta

30.3

Rank #283 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Gemini 3.1 Pro 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 reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 13.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro 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 $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro 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 3.1 Pro PreviewLlama-3.3-70B-Instruct
ProviderGoogleMeta
Noometry Index56.730.3
Released2026-02-192024-12-06
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$2$0.10
Output $ / M tokens$12$0.32
Results tracked7143

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

Category by category

Coding Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 42.7 (#88), Llama-3.3-70B-Instruct: 30.6 (#284)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
SciCode58.9%26%
WeirdML72.1%14.4%
LMArena Coding14831268
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1446—
GSO22.6%—
BigCodeBench Instruct—46.9%
LiveBench Coding—36.6%
MirrorCode8.9%—
BigCodeBench Complete—57.5%
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#33), Llama-3.3-70B-Instruct: 25.6 (#100)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
BALROG57%23%
Terminal-Bench80.2%—
APEX-Agents35.3%—
Berkeley Function Calling Leaderboard—31.9%
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#9), Llama-3.3-70B-Instruct: 13.7 (#325)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
SimpleBench79.6%19.9%
CritPt17.7%0%
LMArena Hard Prompts14841257
DTBench97.1%59.5%
LMCA53.8%17.5%
Epoch Capabilities Index154.92127.32
ForecastBench5958.6
ARC-AGI-277.1%—
NYT Connections (extended)97.4%—
ARC-AGI-198%—
Chess Puzzles55%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
LiveBench Reasoning—50.8%
Mystery Game Puzzles34%—
LiveBench Data Analysis—49.5%
LiveBench—50.2%

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 61.8 (#28), Llama-3.3-70B-Instruct: 14.3 (#292)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
OTIS Mock AIME 2024-202595.6%5.1%
LMArena Math14851268
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
LiveBench Math—42.2%
MATH Level 5—41.6%
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Llama-3.3-70B-Instruct: 30.5 (#220)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
GPQA Diamond94.4%47.4%
Vectara Hallucination Rate10.4%4.1%
LMArena Expert14841225
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
Confabulations—22.8%
MMLU—86.3%

Multimodal Not comparable

Gemini 3.1 Pro Preview: 38.1 (#60), Llama-3.3-70B-Instruct: —

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.1 (#11), Llama-3.3-70B-Instruct: 40.1 (#215)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
LMArena Non-English14751236
LMArena Chinese15281217
LMArena French14881280
LMArena German14911251
LMArena Japanese14941149
LMArena Korean14581142
LMArena Russian14961252
LMArena Spanish14801269

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.1 (#31), Llama-3.3-70B-Instruct: 71.3 (#152)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
LMArena Instruction Following14651242
LiveBench Instruction Following—82.7%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.3 (#17), Llama-3.3-70B-Instruct: 26.4 (#290)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
LMArena Longer Query14821256
Fiction.LiveBench—33.3%
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.3 (#36), Llama-3.3-70B-Instruct: 47.8 (#203)

BenchmarkGemini 3.1 Pro PreviewLlama-3.3-70B-Instruct
LMArena Text14801274
LMArena Creative Writing14821250
LMArena Multi-Turn14861279
EQ-Bench Creative Writing1491—
EQ-Bench 41142—
LiveBench Language—39.2%

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Llama-3.3-70B-Instruct?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 30.3 on the Noometry Index. Llama-3.3-70B-Instruct costs 29× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro 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 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Llama-3.3-70B-Instruct better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 30.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3.1 Pro Preview and Llama-3.3-70B-Instruct share?

29 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Llama-3.3-70B-Instruct has 43.

Related comparisons

Go deeper