Noometry

Model comparison

Llama-3.3-70B-Instruct vs Mistral

Llama-3.3-70B-Instruct and Mistral score almost the same on the Noometry Index (30.6 vs 29.9), so choose on price, context window or the category you care about most.

Last verified . 17 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Mistral Mistral AI

29.9

Rank #303 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Mistral in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Llama-3.3-70B-Instruct leads 71.1 to 52.6.
  • Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.

Side by side

Llama-3.3-70B-InstructMistral
ProviderMetaMistral AI
Noometry Index30.629.9
Released2024-12-06—
WeightsOpenProprietary
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.32—
Results tracked4322

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

Category by category

Coding Mistral leads

Llama-3.3-70B-Instruct: 31.0 (#290), Mistral: 33.8 (#250)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Coding12681162
SciCode26%—
WeirdML14.4%—
BigCodeBench Instruct46.9%—
LiveBench Coding36.6%—
BigCodeBench Complete57.5%—

Agentic & Tool Use Not comparable

Llama-3.3-70B-Instruct: 25.8 (#105), Mistral: —

BenchmarkLlama-3.3-70B-InstructMistral
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Mistral leads

Llama-3.3-70B-Instruct: 14.1 (#327), Mistral: 22.2 (#200)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Hard Prompts12571149
SimpleBench19.9%—
CritPt0%—
LiveBench Reasoning50.8%—
DTBench59.5%—
LiveBench Data Analysis49.5%—
LMCA17.5%—
Epoch Capabilities Index127.33—
ForecastBench58.6—
LiveBench50.2%—

Math Mistral leads

Llama-3.3-70B-Instruct: 15.3 (#298), Mistral: 22.3 (#278)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Math12671180
OTIS Mock AIME 2024-20255.1%—
Omni-MATH—7.2%
LiveBench Math42.2%—
MATH Level 541.6%—

Knowledge Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 30.6 (#226), Mistral: 16.6 (#288)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Expert12251125
GPQA Diamond47.4%—
MMLU-Pro—27.7%
Confabulations22.8%—
Vectara Hallucination Rate4.1%—
GPQA (HELM)—30.3%
MMLU86.3%—

Multilingual Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 39.9 (#220), Mistral: 32.8 (#254)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Non-English12361129
LMArena Chinese12171109
LMArena French12811180
LMArena German12511155
LMArena Japanese11501013
LMArena Korean11431032
LMArena Russian12521168
LMArena Spanish12701143

Instruction Following Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 71.1 (#157), Mistral: 52.6 (#288)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Instruction Following12421152
LiveBench Instruction Following82.7%—
IFEval—56.8%

Long Context Mistral leads

Llama-3.3-70B-Instruct: 26.4 (#295), Mistral: 35.0 (#245)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Longer Query12561153
Fiction.LiveBench33.3%—

Writing & Preference Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 47.6 (#207), Mistral: 37.0 (#260)

BenchmarkLlama-3.3-70B-InstructMistral
LMArena Text12741165
LMArena Creative Writing12501158
LMArena Multi-Turn12801147
WildBench—66%
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Mistral?

Llama-3.3-70B-Instruct and Mistral score almost the same on the Noometry Index (30.6 vs 29.9), so choose on price, context window or the category you care about most.

Is Llama-3.3-70B-Instruct or Mistral better for coding?

Mistral scores higher on coding benchmarks: 33.8 versus 31.0 in the Noometry coding category.

How many benchmarks do Llama-3.3-70B-Instruct and Mistral share?

17 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Mistral has 22.

Related comparisons

Go deeper