Model comparison

Devstral Small 2505 vs Seed 2.0 Pro

Seed 2.0 Pro is the stronger model overall, scoring 42.5 to 33.9 on the Noometry Index. Devstral Small 2505 costs 7.5× less per token, which makes it the better buy when Seed 2.0 Pro's lead doesn't matter for your workload.

Last verified . 0 shared benchmarks.

Devstral Small 2505 Mistral AI

33.9

Rank #228 Reported

Seed 2.0 Pro ByteDance Seed

42.5

Rank #97 Confirmed

Summary

  • The widest gap is in coding, where Seed 2.0 Pro leads 42.9 to 38.6.
  • Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.50 / $3 for Seed 2.0 Pro.
  • Seed 2.0 Pro accepts more context: 256K tokens versus 128K.
  • Devstral Small 2505 has downloadable open weights; the other is API-only.

Side by side

Devstral Small 2505 and Seed 2.0 Pro specifications
Devstral Small 2505Seed 2.0 Pro
ProviderMistral AIByteDance Seed
Noometry Index33.942.5
Released2025-05-072026-02-14
WeightsOpenProprietary
Context window128K256K
Max output128K128K
Input $ / M tokens$0.10$0.50
Output $ / M tokens$0.30$3
Results tracked420

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

Category by category

Coding Seed 2.0 Pro leads

Devstral Small 2505: 38.6 (#160), Seed 2.0 Pro: 42.9 (#84)

Coding benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
SWE-bench Verified (bash only)56.4%—
SciCode28.8%—
LMArena Coding—1472

Reasoning Seed 2.0 Pro leads

Devstral Small 2505: 19.1 (#243), Seed 2.0 Pro: 23.1 (#167)

Reasoning benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
Kagi LLM Benchmark37.7%—
NYT Connections (extended)—28.4%
CritPt0%—
Thematic Generalization—57.1%
LMArena Hard Prompts—1453

Math Not comparable

Devstral Small 2505: —, Seed 2.0 Pro: 36.5 (#110)

Math benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
LMArena Math—1440

Knowledge Not comparable

Devstral Small 2505: —, Seed 2.0 Pro: 39.6 (#119)

Knowledge benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
LMArena Expert—1440

Multimodal Not comparable

Devstral Small 2505: —, Seed 2.0 Pro: 40.8 (#34)

Multimodal benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
LMArena Vision—1275

Multilingual Not comparable

Devstral Small 2505: —, Seed 2.0 Pro: 54.8 (#37)

Multilingual benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
LMArena Non-English—1442
LMArena Chinese—1490
LMArena French—1470
LMArena German—1443
LMArena Japanese—1408
LMArena Korean—1412
LMArena Russian—1450
LMArena Spanish—1460

Instruction Following Not comparable

Devstral Small 2505: —, Seed 2.0 Pro: 74.7 (#86)

Instruction Following benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
LMArena Instruction Following—1414

Long Context Not comparable

Devstral Small 2505: —, Seed 2.0 Pro: 43.6 (#85)

Long Context benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
LMArena Longer Query—1428

Writing & Preference Not comparable

Devstral Small 2505: —, Seed 2.0 Pro: 63.0 (#66)

Writing & Preference benchmarks
BenchmarkDevstral Small 2505Seed 2.0 Pro
LMArena Text—1448
LMArena Creative Writing—1406
LMArena Multi-Turn—1441

Frequently asked questions

Is Devstral Small 2505 better than Seed 2.0 Pro?

Seed 2.0 Pro is the stronger model overall, scoring 42.5 to 33.9 on the Noometry Index. Devstral Small 2505 costs 7.5× less per token, which makes it the better buy when Seed 2.0 Pro's lead doesn't matter for your workload.

Which is cheaper, Devstral Small 2505 or Seed 2.0 Pro?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Seed 2.0 Pro lists at $0.50 and $3.

Is Devstral Small 2505 or Seed 2.0 Pro better for coding?

Seed 2.0 Pro scores higher on coding benchmarks: 42.9 versus 38.6 in the Noometry coding category.

Which has the bigger context window?

Seed 2.0 Pro does, with 256K tokens against 128K.

How many benchmarks do Devstral Small 2505 and Seed 2.0 Pro share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Seed 2.0 Pro has 20.

Related comparisons

Go deeper