Model comparison

Devstral Small 2505 vs Hy4 preview

Hy4 preview is the stronger model overall, scoring 44.6 to 33.9 on the Noometry Index. Devstral Small 2505 costs 8.3× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

Last verified . 0 shared benchmarks.

Devstral Small 2505 Mistral AI

33.9

Rank #228 Reported

Hy4 preview Tencent

44.6

Rank #73 Reported

Summary

  • The widest gap is in coding, where Hy4 preview leads 51.4 to 38.6.
  • Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
  • Hy4 preview accepts more context: 1.05M tokens versus 128K.

Side by side

Devstral Small 2505 and Hy4 preview specifications
Devstral Small 2505Hy4 preview
ProviderMistral AITencent
Noometry Index33.944.6
Released2025-05-072026-08-28
WeightsOpenOpen
Context window128K1.05M
Max output128K64K
Input $ / M tokens$0.10$0.83
Output $ / M tokens$0.30$2.50
Results tracked43

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

Category by category

Coding Hy4 preview leads

Devstral Small 2505: 38.6 (#160), Hy4 preview: 51.4 (#36)

Coding benchmarks
BenchmarkDevstral Small 2505Hy4 preview
SWE-bench Verified (bash only)56.4%—
LMArena WebDev—1633
SciCode28.8%—

Reasoning Hy4 preview leads

Devstral Small 2505: 19.1 (#243), Hy4 preview: 30.6 (#75)

Reasoning benchmarks
BenchmarkDevstral Small 2505Hy4 preview
Kagi LLM Benchmark37.7%—
NYT Connections (extended)—68.2%
CritPt0%—

Math Not comparable

Devstral Small 2505: —, Hy4 preview: 54.5 (#37)

Math benchmarks
BenchmarkDevstral Small 2505Hy4 preview
ProofBench—75%

Frequently asked questions

Is Devstral Small 2505 better than Hy4 preview?

Hy4 preview is the stronger model overall, scoring 44.6 to 33.9 on the Noometry Index. Devstral Small 2505 costs 8.3× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

Which is cheaper, Devstral Small 2505 or Hy4 preview?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Hy4 preview lists at $0.83 and $2.50.

Is Devstral Small 2505 or Hy4 preview better for coding?

Hy4 preview scores higher on coding benchmarks: 51.4 versus 38.6 in the Noometry coding category.

Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 128K.

How many benchmarks do Devstral Small 2505 and Hy4 preview share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Hy4 preview has 3.

Related comparisons

Go deeper