Noometry

Model comparison

GPT-3.5-turbo vs Solar Pro4

Solar Pro4 is the stronger model overall, scoring 42.1 to 23.2 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-3.5-turbo OpenAI

23.2

Rank #350 Confirmed

Solar Pro4 Upstage

42.1

Rank #121 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Solar Pro4 leads 38.8 to 6.3.
  • Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
  • Solar Pro4 accepts more context: 524K tokens versus 16K.

Side by side

GPT-3.5-turboSolar Pro4
ProviderOpenAIUpstage
Noometry Index23.242.1
Released2023-03-012026-08-06
WeightsProprietaryProprietary
Context window16K524K
Max output4K131K
Input $ / M tokens$0.50$0.30
Output $ / M tokens$1.50$1.20
Results tracked4418

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

Category by category

Coding Solar Pro4 leads

GPT-3.5-turbo: 23.9 (#331), Solar Pro4: 40.1 (#149)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Coding11361437
LMArena WebDev—1371
WeirdML3.5%—
BigCodeBench Instruct39.1%—
BigCodeBench Complete50.6%—
HumanEval+70.7%—
MBPP+69.7%—

Agentic & Tool Use Not comparable

GPT-3.5-turbo: —, Solar Pro4: —

BenchmarkGPT-3.5-turboSolar Pro4
METR Time Horizons21.5%—

Reasoning Solar Pro4 leads

GPT-3.5-turbo: 13.8 (#332), Solar Pro4: 28.5 (#104)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Hard Prompts11081399
Chess Puzzles0%—
Mystery Game Puzzles3%—
DTBench48.5%—
LMCA9.7%—
Adversarial NLI58.1%—
BIG-Bench Hard61.6%—
CommonsenseQA 2.057%—
Epoch Capabilities Index118.55—
ForecastBench50.4—
WinoGrande81.6%—

Math Solar Pro4 leads

GPT-3.5-turbo: 6.3 (#327), Solar Pro4: 38.8 (#128)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Math11421416
FrontierMath (Tiers 1-3)0%—
OTIS Mock AIME 2024-20252.2%—
MATH Level 515.9%—
GSM8K57.8%—

Knowledge Solar Pro4 leads

GPT-3.5-turbo: 10.0 (#303), Solar Pro4: 39.8 (#129)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Expert10701427
GPQA Diamond28%—
ARC (AI2) Challenge87.4%—
BoolQ87%—
MMLU71.4%—
OpenBookQA86%—
TriviaQA85.8%—

Multilingual Solar Pro4 leads

GPT-3.5-turbo: 31.5 (#258), Solar Pro4: 48.7 (#139)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Non-English11081361
LMArena Chinese10751415
LMArena French11181397
LMArena German10901364
LMArena Japanese10431309
LMArena Korean10191382
LMArena Russian11231360
LMArena Spanish11211401

Instruction Following Solar Pro4 leads

GPT-3.5-turbo: 57.9 (#262), Solar Pro4: 72.7 (#132)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Instruction Following11191377

Long Context Solar Pro4 leads

GPT-3.5-turbo: 34.0 (#254), Solar Pro4: 42.1 (#130)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Longer Query11211381

Writing & Preference Solar Pro4 leads

GPT-3.5-turbo: 25.3 (#305), Solar Pro4: 56.5 (#138)

BenchmarkGPT-3.5-turboSolar Pro4
LMArena Text11251386
LMArena Creative Writing10921316
LMArena Multi-Turn11171385
EQ-Bench Creative Writing451—

Frequently asked questions

Is GPT-3.5-turbo better than Solar Pro4?

Solar Pro4 is the stronger model overall, scoring 42.1 to 23.2 on the Noometry Index.

Which is cheaper, GPT-3.5-turbo or Solar Pro4?

Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.

Is GPT-3.5-turbo or Solar Pro4 better for coding?

Solar Pro4 scores higher on coding benchmarks: 40.1 versus 23.9 in the Noometry coding category.

Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 16K.

How many benchmarks do GPT-3.5-turbo and Solar Pro4 share?

17 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Solar Pro4 has 18.

Related comparisons

Go deeper