Noometry

Model comparison

GPT-4 vs Hunyuan Large Vision

Hunyuan Large Vision is the stronger model overall, scoring 37.0 to 28.9 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-4 OpenAI

28.9

Rank #308 Confirmed

Hunyuan Large Vision Tencent

37.0

Rank #198 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-4 scores higher in 1 category and Hunyuan Large Vision in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Hunyuan Large Vision leads 32.8 to 10.1.

Side by side

GPT-4Hunyuan Large Vision
ProviderOpenAITencent
Noometry Index28.937.0
Released2023-03-14—
WeightsProprietaryProprietary
Context window8K—
Max output8K—
Input $ / M tokens$30—
Output $ / M tokens$60—
Results tracked3813

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

Category by category

Coding Hunyuan Large Vision leads

GPT-4: 31.2 (#277), Hunyuan Large Vision: 37.6 (#176)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Coding12541307
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Hunyuan Large Vision: —

BenchmarkGPT-4Hunyuan Large Vision
METR Time Horizons36.1%—

Reasoning Hunyuan Large Vision leads

GPT-4: 17.3 (#285), Hunyuan Large Vision: 23.8 (#160)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Hard Prompts12411257
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.88—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Hunyuan Large Vision leads

GPT-4: 10.1 (#304), Hunyuan Large Vision: 32.8 (#184)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Math12691269
OTIS Mock AIME 2024-20251.1%—
MATH Level 523%—
GSM8K92%—

Knowledge Hunyuan Large Vision leads

GPT-4: 18.4 (#277), Hunyuan Large Vision: 33.7 (#191)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Expert12111250
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Hunyuan Large Vision: 35.1 (#79)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Vision—1180

Multilingual Too close to call

GPT-4: 40.8 (#210), Hunyuan Large Vision: 40.1 (#216)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Non-English12461236
LMArena Chinese12421289
LMArena Russian12511243
LMArena French1282—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following Too close to call

GPT-4: 65.5 (#217), Hunyuan Large Vision: 66.0 (#210)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Instruction Following12411250

Long Context Hunyuan Large Vision leads

GPT-4: 37.7 (#207), Hunyuan Large Vision: 38.8 (#184)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Longer Query12441279

Writing & Preference Hunyuan Large Vision leads

GPT-4: 35.0 (#263), Hunyuan Large Vision: 46.7 (#211)

BenchmarkGPT-4Hunyuan Large Vision
LMArena Text12631263
LMArena Creative Writing12441250
LMArena Multi-Turn12571253
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Hunyuan Large Vision?

Hunyuan Large Vision is the stronger model overall, scoring 37.0 to 28.9 on the Noometry Index.

Is GPT-4 or Hunyuan Large Vision better for coding?

Hunyuan Large Vision scores higher on coding benchmarks: 37.6 versus 31.2 in the Noometry coding category.

How many benchmarks do GPT-4 and Hunyuan Large Vision share?

12 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Hunyuan Large Vision has 13.

Related comparisons

Go deeper