Noometry

Model comparison

Qwen2.5 72B Instruct vs Yi-34B

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 27.8 on the Noometry Index.

Last verified . 22 shared benchmarks.

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 7 categories and Yi-34B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen2.5 72B Instruct leads 27.0 to 7.5.
  • The biggest single-benchmark swing is MATH Level 5: 63.2% for Qwen2.5 72B Instruct and 5.1% for Yi-34B.

Side by side

Qwen2.5 72B InstructYi-34B
ProviderAlibaba (Qwen)01.AI
Noometry Index31.927.8
Released2024-092023-11-02
WeightsOpenOpen
Context window131K—
Max output8K—
Input $ / M tokens$1.40—
Output $ / M tokens$5.60—
Results tracked4323

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

Category by category

Coding Too close to call

Qwen2.5 72B Instruct: 33.2 (#260), Yi-34B: 32.3 (#274)

BenchmarkQwen2.5 72B InstructYi-34B
LMArena Coding12921112
WeirdML16%—
BigCodeBench Instruct45.8%—
BigCodeBench Complete55.9%—

Agentic & Tool Use Not comparable

Qwen2.5 72B Instruct: 22.1 (#133), Yi-34B: —

BenchmarkQwen2.5 72B InstructYi-34B
TheAgentCompany5.7%—
BALROG16.2%—
METR Time Horizons35.8%—

Reasoning Qwen2.5 72B Instruct leads

Qwen2.5 72B Instruct: 22.3 (#199), Yi-34B: 21.2 (#226)

BenchmarkQwen2.5 72B InstructYi-34B
LMArena Hard Prompts12711104
BIG-Bench Hard79.8%71.7%
Epoch Capabilities Index129117.39
DTBench62.9%—
LMCA13.4%—
ForecastBench57.5—
HellaSwag84.8%—
PIQA82.6%—
WinoGrande82.3%—

Math Yi-34B leads

Qwen2.5 72B Instruct: 19.3 (#287), Yi-34B: 21.6 (#282)

BenchmarkQwen2.5 72B InstructYi-34B
LMArena Math12831114
MATH Level 563.2%5.1%
OTIS Mock AIME 2024-20258.1%—
Omni-MATH33%—
GSM8K—76%

Knowledge Qwen2.5 72B Instruct leads

Qwen2.5 72B Instruct: 27.0 (#253), Yi-34B: 7.5 (#309)

BenchmarkQwen2.5 72B InstructYi-34B
GPQA Diamond49.1%14.7%
LMArena Expert12451061
MMLU85.3%76.3%
MMLU-Pro63.1%—
Confabulations19.1%—
GPQA (HELM)42.6%—
ARC (AI2) Challenge94.5%—
TriviaQA71.9%—

Multilingual Qwen2.5 72B Instruct leads

Qwen2.5 72B Instruct: 41.0 (#213), Yi-34B: 29.7 (#264)

BenchmarkQwen2.5 72B InstructYi-34B
LMArena Non-English12521079
LMArena Chinese12721176
LMArena French12801081
LMArena German12341042
LMArena Japanese1180993
LMArena Korean1188959
LMArena Russian12641050
LMArena Spanish12561070

Instruction Following Qwen2.5 72B Instruct leads

Qwen2.5 72B Instruct: 65.5 (#221), Yi-34B: 56.2 (#274)

BenchmarkQwen2.5 72B InstructYi-34B
LMArena Instruction Following12541091
IFEval80.6%—

Long Context Qwen2.5 72B Instruct leads

Qwen2.5 72B Instruct: 38.9 (#188), Yi-34B: 33.2 (#264)

BenchmarkQwen2.5 72B InstructYi-34B
LMArena Longer Query12821094

Writing & Preference Qwen2.5 72B Instruct leads

Qwen2.5 72B Instruct: 46.7 (#215), Yi-34B: 34.1 (#273)

BenchmarkQwen2.5 72B InstructYi-34B
LMArena Text12691129
LMArena Creative Writing12211108
LMArena Multi-Turn12721113
WildBench80.2%—

Frequently asked questions

Is Qwen2.5 72B Instruct better than Yi-34B?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 27.8 on the Noometry Index.

Is Qwen2.5 72B Instruct or Yi-34B better for coding?

They score almost the same on coding (33.2 vs 32.3); test both on your own repository before choosing.

How many benchmarks do Qwen2.5 72B Instruct and Yi-34B share?

22 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper