Noometry

Model comparison

Llama-3.3-70B-Instruct vs Yi-34B

Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.3 to 27.4 on the Noometry Index.

Last verified . 21 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.3

Rank #283 Confirmed

Yi-34B 01.AI

27.4

Rank #325 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Yi-34B in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Llama-3.3-70B-Instruct leads 30.5 to 7.5.
  • The biggest single-benchmark swing is MATH Level 5: 41.6% for Llama-3.3-70B-Instruct and 5.1% for Yi-34B.

Side by side

Llama-3.3-70B-InstructYi-34B
ProviderMeta01.AI
Noometry Index30.327.4
Released2024-12-062023-11-02
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.32—
Results tracked4323

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

Category by category

Coding Yi-34B leads

Llama-3.3-70B-Instruct: 30.6 (#284), Yi-34B: 31.8 (#269)

BenchmarkLlama-3.3-70B-InstructYi-34B
LMArena Coding12681112
SciCode26%—
WeirdML14.4%—
BigCodeBench Instruct46.9%—
LiveBench Coding36.6%—
BigCodeBench Complete57.5%—

Agentic & Tool Use Not comparable

Llama-3.3-70B-Instruct: 25.6 (#100), Yi-34B: —

BenchmarkLlama-3.3-70B-InstructYi-34B
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Yi-34B leads

Llama-3.3-70B-Instruct: 13.7 (#325), Yi-34B: 20.3 (#222)

BenchmarkLlama-3.3-70B-InstructYi-34B
LMArena Hard Prompts12571104
Epoch Capabilities Index127.32117.28
SimpleBench19.9%—
CritPt0%—
LiveBench Reasoning50.8%—
DTBench59.5%—
LiveBench Data Analysis49.5%—
LMCA17.5%—
BIG-Bench Hard—71.7%
ForecastBench58.6—
LiveBench50.2%—

Math Yi-34B leads

Llama-3.3-70B-Instruct: 14.3 (#292), Yi-34B: 19.8 (#277)

BenchmarkLlama-3.3-70B-InstructYi-34B
LMArena Math12681114
MATH Level 541.6%5.1%
OTIS Mock AIME 2024-20255.1%—
LiveBench Math42.2%—
GSM8K—76%

Knowledge Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 30.5 (#220), Yi-34B: 7.5 (#304)

BenchmarkLlama-3.3-70B-InstructYi-34B
GPQA Diamond47.4%14.7%
LMArena Expert12251061
MMLU86.3%76.3%
Confabulations22.8%—
Vectara Hallucination Rate4.1%—

Multilingual Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 40.1 (#215), Yi-34B: 29.9 (#259)

BenchmarkLlama-3.3-70B-InstructYi-34B
LMArena Non-English12361079
LMArena Chinese12171175
LMArena French12801080
LMArena German12511042
LMArena Japanese1149993
LMArena Korean1142959
LMArena Russian12521050
LMArena Spanish12691070

Instruction Following Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 71.3 (#152), Yi-34B: 56.4 (#269)

BenchmarkLlama-3.3-70B-InstructYi-34B
LMArena Instruction Following12421091
LiveBench Instruction Following82.7%—

Long Context Yi-34B leads

Llama-3.3-70B-Instruct: 26.4 (#290), Yi-34B: 33.2 (#259)

BenchmarkLlama-3.3-70B-InstructYi-34B
LMArena Longer Query12561094
Fiction.LiveBench33.3%—

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

Llama-3.3-70B-Instruct: 47.8 (#203), Yi-34B: 34.3 (#268)

BenchmarkLlama-3.3-70B-InstructYi-34B
LMArena Text12741129
LMArena Creative Writing12501108
LMArena Multi-Turn12791113
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Yi-34B?

Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.3 to 27.4 on the Noometry Index.

Is Llama-3.3-70B-Instruct or Yi-34B better for coding?

Yi-34B scores higher on coding benchmarks: 31.8 versus 30.6 in the Noometry coding category.

How many benchmarks do Llama-3.3-70B-Instruct and Yi-34B share?

21 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper