Model comparison

Hunyuan Standard 2025 02 10 vs Step 3.7 Flash

Hunyuan Standard 2025 02 10 and Step 3.7 Flash score almost the same on the Noometry Index (37.9 vs 37.3), so choose on price, context window or the category you care about most.

Last verified . 0 shared benchmarks.

Hunyuan Standard 2025 02 10 Tencent

37.9

Rank #193 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • The widest gap is in math, where Step 3.7 Flash leads 42.9 to 35.6.
  • Step 3.7 Flash has downloadable open weights; the other is API-only.

Side by side

Hunyuan Standard 2025 02 10 and Step 3.7 Flash specifications
Hunyuan Standard 2025 02 10Step 3.7 Flash
ProviderTencentStepFun
Noometry Index37.937.3
Released—2026-05-29
WeightsProprietaryOpen
Context window—256K
Max output—256K
Input $ / M tokens—$0.18
Output $ / M tokens—$1.11
Results tracked125

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

Category by category

Coding Step 3.7 Flash leads

Hunyuan Standard 2025 02 10: 37.1 (#197), Step 3.7 Flash: 40.0 (#150)

Coding benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
SciCode—40%
LMArena Coding1270—
ALE-Bench—694.12

Reasoning Hunyuan Standard 2025 02 10 leads

Hunyuan Standard 2025 02 10: 25.0 (#154), Step 3.7 Flash: 21.6 (#219)

Reasoning benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
NYT Connections (extended)—39.7%
CritPt—2.3%
LMArena Hard Prompts1264—

Math Step 3.7 Flash leads

Hunyuan Standard 2025 02 10: 35.6 (#179), Step 3.7 Flash: 42.9 (#82)

Math benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
MathArena Final-Answer Competitions—68.5%
LMArena Math1274—

Knowledge Not comparable

Hunyuan Standard 2025 02 10: 34.2 (#197), Step 3.7 Flash: —

Knowledge benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
LMArena Expert1248—

Multilingual Not comparable

Hunyuan Standard 2025 02 10: 41.7 (#203), Step 3.7 Flash: —

Multilingual benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
LMArena Non-English1262—
LMArena Chinese1319—
LMArena Russian1258—

Instruction Following Not comparable

Hunyuan Standard 2025 02 10: 65.5 (#219), Step 3.7 Flash: —

Instruction Following benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
LMArena Instruction Following1245—

Long Context Not comparable

Hunyuan Standard 2025 02 10: 39.5 (#173), Step 3.7 Flash: —

Long Context benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
LMArena Longer Query1301—

Writing & Preference Not comparable

Hunyuan Standard 2025 02 10: 47.2 (#214), Step 3.7 Flash: —

Writing & Preference benchmarks
BenchmarkHunyuan Standard 2025 02 10Step 3.7 Flash
LMArena Text1274—
LMArena Creative Writing1242—
LMArena Multi-Turn1275—

Frequently asked questions

Is Hunyuan Standard 2025 02 10 better than Step 3.7 Flash?

Hunyuan Standard 2025 02 10 and Step 3.7 Flash score almost the same on the Noometry Index (37.9 vs 37.3), so choose on price, context window or the category you care about most.

Is Hunyuan Standard 2025 02 10 or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 37.1 in the Noometry coding category.

How many benchmarks do Hunyuan Standard 2025 02 10 and Step 3.7 Flash share?

0 benchmarks have published results for both models. Hunyuan Standard 2025 02 10 has 12 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper