Noometry

Model comparison

Claude 3 Opus vs Llama-3.3-70B-Instruct

Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 29.5 on the Noometry Index.

Last verified . 37 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Claude 3 Opus scores higher in 4 categories and Llama-3.3-70B-Instruct in 5 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Claude 3 Opus leads 38.2 to 26.4.
  • The biggest single-benchmark swing is LiveBench Instruction Following: 63.9% for Claude 3 Opus and 82.7% for Llama-3.3-70B-Instruct.
  • Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusLlama-3.3-70B-Instruct
ProviderAnthropicMeta
Noometry Index29.530.6
Released2024-02-292024-12-06
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.32
Results tracked4643

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

Category by category

Coding Claude 3 Opus leads

Claude 3 Opus: 32.9 (#267), Llama-3.3-70B-Instruct: 31.0 (#290)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
WeirdML19.2%14.4%
BigCodeBench Instruct45.5%46.9%
LiveBench Coding38.6%36.6%
LMArena Coding12641268
BigCodeBench Complete57.4%57.5%
SciCode—26%
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Llama-3.3-70B-Instruct leads

Claude 3 Opus: 24.6 (#116), Llama-3.3-70B-Instruct: 25.8 (#105)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
Berkeley Function Calling Leaderboard—31.9%
Cybench10%—
BALROG—23%
METR Time Horizons29.5%—

Reasoning Too close to call

Claude 3 Opus: 14.6 (#324), Llama-3.3-70B-Instruct: 14.1 (#327)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
SimpleBench23.5%19.9%
LiveBench Reasoning40.6%50.8%
LMArena Hard Prompts12451257
DTBench61.6%59.5%
LiveBench Data Analysis57.9%49.5%
LMCA17%17.5%
Epoch Capabilities Index126.91127.33
ForecastBench58.458.6
LiveBench49.2%50.2%
CritPt—0%
Chess Puzzles5%—
EnigmaEval0.8%—
WinoGrande88.5%—

Math Too close to call

Claude 3 Opus: 14.8 (#299), Llama-3.3-70B-Instruct: 15.3 (#298)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
OTIS Mock AIME 2024-20254.7%5.1%
LiveBench Math43.6%42.2%
LMArena Math12731267
MATH Level 537.5%41.6%

Knowledge Llama-3.3-70B-Instruct leads

Claude 3 Opus: 24.5 (#267), Llama-3.3-70B-Instruct: 30.6 (#226)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
GPQA Diamond47.2%47.4%
Confabulations22.7%22.8%
LMArena Expert12231225
MMLU84.6%86.3%
SimpleQA Verified12.6%—
Vectara Hallucination Rate—4.1%

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Llama-3.3-70B-Instruct: —

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Llama-3.3-70B-Instruct: 39.9 (#220)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
LMArena Non-English12581236
LMArena Chinese12481217
LMArena French12751281
LMArena German12581251
LMArena Japanese12041150
LMArena Korean11871143
LMArena Russian12801252
LMArena Spanish12461270

Instruction Following Llama-3.3-70B-Instruct leads

Claude 3 Opus: 64.1 (#228), Llama-3.3-70B-Instruct: 71.1 (#157)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
LiveBench Instruction Following63.9%82.7%
LMArena Instruction Following12481242

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Llama-3.3-70B-Instruct: 26.4 (#295)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
LMArena Longer Query12591256
Fiction.LiveBench—33.3%

Writing & Preference Too close to call

Claude 3 Opus: 47.2 (#213), Llama-3.3-70B-Instruct: 47.6 (#207)

BenchmarkClaude 3 OpusLlama-3.3-70B-Instruct
LMArena Text12621274
LMArena Creative Writing12351250
LMArena Multi-Turn12751280
LiveBench Language50.4%39.2%

Frequently asked questions

Is Claude 3 Opus better than Llama-3.3-70B-Instruct?

Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 29.5 on the Noometry Index.

Is Claude 3 Opus or Llama-3.3-70B-Instruct better for coding?

Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 31.0 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Llama-3.3-70B-Instruct share?

37 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Llama-3.3-70B-Instruct has 43.

Related comparisons

Go deeper