Noometry

Model comparison

Claude 3 Opus vs Yi-34B

Claude 3 Opus is the stronger model overall, scoring 29.5 to 27.8 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3 Opus scores higher in 6 categories and Yi-34B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Opus leads 24.5 to 7.5.
  • The biggest single-benchmark swing is GPQA Diamond: 47.2% for Claude 3 Opus and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusYi-34B
ProviderAnthropic01.AI
Noometry Index29.527.8
Released2024-02-292023-11-02
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4623

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

Category by category

Coding Too close to call

Claude 3 Opus: 32.9 (#267), Yi-34B: 32.3 (#274)

BenchmarkClaude 3 OpusYi-34B
LMArena Coding12641112
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Yi-34B: —

BenchmarkClaude 3 OpusYi-34B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Yi-34B leads

Claude 3 Opus: 14.6 (#324), Yi-34B: 21.2 (#226)

BenchmarkClaude 3 OpusYi-34B
LMArena Hard Prompts12451104
Epoch Capabilities Index126.91117.39
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
BIG-Bench Hard—71.7%
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Yi-34B leads

Claude 3 Opus: 14.8 (#299), Yi-34B: 21.6 (#282)

BenchmarkClaude 3 OpusYi-34B
LMArena Math12731114
MATH Level 537.5%5.1%
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
GSM8K—76%

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Yi-34B: 7.5 (#309)

BenchmarkClaude 3 OpusYi-34B
GPQA Diamond47.2%14.7%
LMArena Expert12231061
MMLU84.6%76.3%
SimpleQA Verified12.6%—
Confabulations22.7%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Yi-34B: —

BenchmarkClaude 3 OpusYi-34B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Yi-34B: 29.7 (#264)

BenchmarkClaude 3 OpusYi-34B
LMArena Non-English12581079
LMArena Chinese12481176
LMArena French12751081
LMArena German12581042
LMArena Japanese1204993
LMArena Korean1187959
LMArena Russian12801050
LMArena Spanish12461070

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Yi-34B: 56.2 (#274)

BenchmarkClaude 3 OpusYi-34B
LMArena Instruction Following12481091
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Yi-34B: 33.2 (#264)

BenchmarkClaude 3 OpusYi-34B
LMArena Longer Query12591094

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Yi-34B: 34.1 (#273)

BenchmarkClaude 3 OpusYi-34B
LMArena Text12621129
LMArena Creative Writing12351108
LMArena Multi-Turn12751113
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Yi-34B?

Claude 3 Opus is the stronger model overall, scoring 29.5 to 27.8 on the Noometry Index.

Is Claude 3 Opus or Yi-34B better for coding?

They score almost the same on coding (32.9 vs 32.3); test both on your own repository before choosing.

How many benchmarks do Claude 3 Opus and Yi-34B share?

21 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper