Noometry

Model comparison

GPT-5.4 mini vs Yi-1.5-34B

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 30.2 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-5.4 mini OpenAI

44.8

Rank #69 Confirmed

Yi-1.5-34B 01.AI

30.2

Rank #286 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Yi-1.5-34B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 14.8.
  • The biggest single-benchmark swing is GPQA Diamond: 86.9% for GPT-5.4 mini and 32% for Yi-1.5-34B.
  • Yi-1.5-34B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniYi-1.5-34B
ProviderOpenAI01.AI
Noometry Index44.830.2
Released2026-03-172024-05-13
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4621

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.0 (#67), Yi-1.5-34B: 31.9 (#267)

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Coding14381169
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
BigCodeBench Instruct—33.9%
BigCodeBench Complete—43.8%
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.6 (#74), Yi-1.5-34B: —

BenchmarkGPT-5.4 miniYi-1.5-34B
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.3 (#77), Yi-1.5-34B: 21.5 (#195)

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Hard Prompts14241160
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Chess Puzzles24%—
Thematic Generalization61.7%—
Mystery Game Puzzles11%—
DTBench80%—
LMCA40.8%—
Epoch Capabilities Index148.83—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.4 (#63), Yi-1.5-34B: 25.3 (#248)

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Math14181182
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
ProofBench21%—
MATH Level 5—25.5%
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.4 (#62), Yi-1.5-34B: 14.8 (#290)

BenchmarkGPT-5.4 miniYi-1.5-34B
GPQA Diamond86.9%32%
LMArena Expert14341144
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.0 (#51), Yi-1.5-34B: —

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 52.1 (#94), Yi-1.5-34B: 32.5 (#251)

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Non-English14051121
LMArena Chinese14461213
LMArena French14401155
LMArena German14071111
LMArena Japanese13751021
LMArena Korean13691005
LMArena Russian14171091
LMArena Spanish14031120

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.3 (#99), Yi-1.5-34B: 59.4 (#252)

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Instruction Following14051139

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 42.9 (#107), Yi-1.5-34B: 34.6 (#243)

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Longer Query14071144

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.2 (#56), Yi-1.5-34B: 37.6 (#252)

BenchmarkGPT-5.4 miniYi-1.5-34B
LMArena Text14111173
LMArena Creative Writing13701135
LMArena Multi-Turn14291153
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Yi-1.5-34B?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 30.2 on the Noometry Index.

Is GPT-5.4 mini or Yi-1.5-34B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 31.9 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and Yi-1.5-34B share?

18 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Yi-1.5-34B has 21.

Related comparisons

Go deeper