Noometry

Model comparison

GPT-4.5 vs Yi-34B

GPT-4.5 is the stronger model overall, scoring 37.2 to 27.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4.5 scores higher in 7 categories and Yi-34B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.5 leads 32.5 to 7.5.
  • The biggest single-benchmark swing is MATH Level 5: 78.6% for GPT-4.5 and 5.1% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Yi-34B
ProviderOpenAI01.AI
Noometry Index37.227.8
Released2025-02-272023-11-02
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4223

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), Yi-34B: 32.3 (#274)

BenchmarkGPT-4.5Yi-34B
LMArena Coding13961112
Aider Polyglot44.9%—
WeirdML39.4%—
LiveBench Coding75.2%—

Agentic & Tool Use Not comparable

GPT-4.5: 27.9 (#97), Yi-34B: —

BenchmarkGPT-4.5Yi-34B
Cybench17.5%—

Reasoning Yi-34B leads

GPT-4.5: 13.9 (#330), Yi-34B: 21.2 (#226)

BenchmarkGPT-4.5Yi-34B
LMArena Hard Prompts14031104
Epoch Capabilities Index136.74117.39
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LiveBench Data Analysis64.3%—
BIG-Bench Hard—71.7%
ForecastBench61.7—
LiveBench69%—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), Yi-34B: 21.6 (#282)

BenchmarkGPT-4.5Yi-34B
LMArena Math14121114
MATH Level 578.6%5.1%
OTIS Mock AIME 2024-202537.8%—
LiveBench Math69.3%—
GSM8K—76%

Knowledge GPT-4.5 leads

GPT-4.5: 32.5 (#211), Yi-34B: 7.5 (#309)

BenchmarkGPT-4.5Yi-34B
GPQA Diamond68.7%14.7%
LMArena Expert13941061
Humanity's Last Exam5.4%—
Confabulations13.6%—
MMLU—76.3%

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Yi-34B: —

BenchmarkGPT-4.5Yi-34B
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), Yi-34B: 29.7 (#264)

BenchmarkGPT-4.5Yi-34B
LMArena Non-English14131079
LMArena Chinese14211176
LMArena French14181081
LMArena German14571042
LMArena Japanese1416993
LMArena Korean1392959
LMArena Russian14191050
LMArena Spanish—1070

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), Yi-34B: 56.2 (#274)

BenchmarkGPT-4.5Yi-34B
LMArena Instruction Following14041091
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Yi-34B: 33.2 (#264)

BenchmarkGPT-4.5Yi-34B
LMArena Longer Query14061094
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), Yi-34B: 34.1 (#273)

BenchmarkGPT-4.5Yi-34B
LMArena Text14171129
LMArena Creative Writing13941108
LMArena Multi-Turn14441113
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Yi-34B?

GPT-4.5 is the stronger model overall, scoring 37.2 to 27.8 on the Noometry Index.

Is GPT-4.5 or Yi-34B better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 32.3 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Yi-34B share?

19 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper