Noometry

Model comparison

GPT-4 Turbo vs Solar Pro4

Solar Pro4 is the stronger model overall, scoring 42.1 to 30.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Solar Pro4 Upstage

42.1

Rank #121 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4 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 9.0.
  • Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Solar Pro4 accepts more context: 524K tokens versus 128K.

Side by side

GPT-4 TurboSolar Pro4
ProviderOpenAIUpstage
Noometry Index30.542.1
Released2023-11-062026-08-06
WeightsProprietaryProprietary
Context window128K524K
Max output4K131K
Input $ / M tokens$10$0.30
Output $ / M tokens$30$1.20
Results tracked3618

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

Category by category

Coding Solar Pro4 leads

GPT-4 Turbo: 33.8 (#249), Solar Pro4: 40.1 (#149)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Coding12681437
LMArena WebDev—1371
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Solar Pro4: —

BenchmarkGPT-4 TurboSolar Pro4
METR Time Horizons36.7%—

Reasoning Solar Pro4 leads

GPT-4 Turbo: 15.3 (#317), Solar Pro4: 28.5 (#104)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Hard Prompts12511399
SimpleBench25.1%—
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Solar Pro4 leads

GPT-4 Turbo: 9.0 (#322), Solar Pro4: 38.8 (#128)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Math12721416
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge Solar Pro4 leads

GPT-4 Turbo: 24.3 (#268), Solar Pro4: 39.8 (#129)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Expert12231427
GPQA Diamond46.6%—
Confabulations28.4%—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Solar Pro4: —

BenchmarkGPT-4 TurboSolar Pro4
LMArena Vision1090—

Multilingual Solar Pro4 leads

GPT-4 Turbo: 40.5 (#216), Solar Pro4: 48.7 (#139)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Non-English12451361
LMArena Chinese12421415
LMArena French12761397
LMArena German12591364
LMArena Japanese11941309
LMArena Korean11871382
LMArena Russian12591360
LMArena Spanish12601401

Instruction Following Solar Pro4 leads

GPT-4 Turbo: 65.8 (#216), Solar Pro4: 72.7 (#132)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Instruction Following12491377

Long Context Solar Pro4 leads

GPT-4 Turbo: 38.0 (#206), Solar Pro4: 42.1 (#130)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Longer Query12541381

Writing & Preference Solar Pro4 leads

GPT-4 Turbo: 47.7 (#206), Solar Pro4: 56.5 (#138)

BenchmarkGPT-4 TurboSolar Pro4
LMArena Text12721386
LMArena Creative Writing12691316
LMArena Multi-Turn12671385

Frequently asked questions

Is GPT-4 Turbo better than Solar Pro4?

Solar Pro4 is the stronger model overall, scoring 42.1 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 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-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Solar Pro4 better for coding?

Solar Pro4 scores higher on coding benchmarks: 40.1 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 128K.

How many benchmarks do GPT-4 Turbo and Solar Pro4 share?

17 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Solar Pro4 has 18.

Related comparisons

Go deeper