Noometry

Model comparison

GPT-4 Turbo vs Step 3.7 Flash

Step 3.7 Flash is the stronger model overall, scoring 36.5 to 30.3 on the Noometry Index.

Last verified . 0 shared benchmarks.

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Step 3.7 Flash StepFun

36.5

Rank #207 Reported

Summary

  • The widest gap is in math, where Step 3.7 Flash leads 40.9 to 8.6.
  • Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Step 3.7 Flash accepts more context: 256K tokens versus 128K.
  • Step 3.7 Flash has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboStep 3.7 Flash
ProviderOpenAIStepFun
Noometry Index30.336.5
Released2023-11-062026-05-29
WeightsProprietaryOpen
Context window128K256K
Max output4K256K
Input $ / M tokens$10$0.18
Output $ / M tokens$30$1.11
Results tracked365

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

Category by category

Coding Step 3.7 Flash leads

GPT-4 Turbo: 33.4 (#247), Step 3.7 Flash: 39.4 (#147)

BenchmarkGPT-4 TurboStep 3.7 Flash
SciCode—40%
WeirdML18%—
BigCodeBench Instruct48.2%—
LMArena Coding1268—
BigCodeBench Complete58.2%—
ALE-Bench—694.12
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Step 3.7 Flash: —

BenchmarkGPT-4 TurboStep 3.7 Flash
METR Time Horizons36.7%—

Reasoning Step 3.7 Flash leads

GPT-4 Turbo: 14.9 (#311), Step 3.7 Flash: 20.9 (#211)

BenchmarkGPT-4 TurboStep 3.7 Flash
SimpleBench25.1%—
NYT Connections (extended)—39.7%
CritPt—2.3%
Chess Puzzles6%—
LMArena Hard Prompts1251—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Step 3.7 Flash leads

GPT-4 Turbo: 8.6 (#316), Step 3.7 Flash: 40.9 (#74)

BenchmarkGPT-4 TurboStep 3.7 Flash
FrontierMath (Tiers 1-3)0.7%—
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-20256.7%—
LMArena Math1272—
MATH Level 546.7%—

Knowledge Not comparable

GPT-4 Turbo: 24.3 (#263), Step 3.7 Flash: —

BenchmarkGPT-4 TurboStep 3.7 Flash
GPQA Diamond46.6%—
Confabulations28.4%—
LMArena Expert1223—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.0 (#104), Step 3.7 Flash: —

BenchmarkGPT-4 TurboStep 3.7 Flash
LMArena Vision1090—

Multilingual Not comparable

GPT-4 Turbo: 40.7 (#211), Step 3.7 Flash: —

BenchmarkGPT-4 TurboStep 3.7 Flash
LMArena Non-English1245—
LMArena Chinese1242—
LMArena French1275—
LMArena German1259—
LMArena Japanese1194—
LMArena Korean1187—
LMArena Russian1259—
LMArena Spanish1260—

Instruction Following Not comparable

GPT-4 Turbo: 66.0 (#211), Step 3.7 Flash: —

BenchmarkGPT-4 TurboStep 3.7 Flash
LMArena Instruction Following1250—

Long Context Not comparable

GPT-4 Turbo: 38.0 (#200), Step 3.7 Flash: —

BenchmarkGPT-4 TurboStep 3.7 Flash
LMArena Longer Query1254—

Writing & Preference Not comparable

GPT-4 Turbo: 47.9 (#201), Step 3.7 Flash: —

BenchmarkGPT-4 TurboStep 3.7 Flash
LMArena Text1272—
LMArena Creative Writing1269—
LMArena Multi-Turn1267—

Frequently asked questions

Is GPT-4 Turbo better than Step 3.7 Flash?

Step 3.7 Flash is the stronger model overall, scoring 36.5 to 30.3 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 39.4 versus 33.4 in the Noometry coding category.

Which has the bigger context window?

Step 3.7 Flash does, with 256K tokens against 128K.

How many benchmarks do GPT-4 Turbo and Step 3.7 Flash share?

0 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper