Noometry

Model comparison

DeepSeek-V3.1-Terminus vs Devstral Small 2505

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.0× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

Last verified . 3 shared benchmarks.

DeepSeek-V3.1-Terminus DeepSeek

43.1

Rank #97 Confirmed

Devstral Small 2505 Mistral AI

34.3

Rank #233 Reported

Summary

  • They share 3 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and Devstral Small 2505 in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 26.4 to 19.7.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 37.7% for Devstral Small 2505.
  • Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.27 / $1 for DeepSeek-V3.1-Terminus.
  • DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.

Side by side

DeepSeek-V3.1-TerminusDevstral Small 2505
ProviderDeepSeekMistral AI
Noometry Index43.134.3
Released2025-09-222025-05-07
WeightsOpenOpen
Context window164K128K
Max output147K128K
Input $ / M tokens$0.27$0.10
Output $ / M tokens$1$0.30
Results tracked164

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

Category by category

Coding DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 42.0 (#113), Devstral Small 2505: 38.9 (#166)

BenchmarkDeepSeek-V3.1-TerminusDevstral Small 2505
SciCode40.6%28.8%
SWE-bench Verified (bash only)—56.4%
LMArena Coding1426—
ALE-Bench745.17—

Reasoning DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 26.4 (#133), Devstral Small 2505: 19.7 (#252)

BenchmarkDeepSeek-V3.1-TerminusDevstral Small 2505
Kagi LLM Benchmark57.4%37.7%
CritPt1.7%0%
LMArena Hard Prompts1426—
DTBench81.3%—
LMCA28.6%—

Math Not comparable

DeepSeek-V3.1-Terminus: 38.5 (#137), Devstral Small 2505: —

BenchmarkDeepSeek-V3.1-TerminusDevstral Small 2505
LMArena Math1402—

Multilingual Not comparable

DeepSeek-V3.1-Terminus: 52.1 (#92), Devstral Small 2505: —

BenchmarkDeepSeek-V3.1-TerminusDevstral Small 2505
LMArena Non-English1407—
LMArena Russian1436—

Instruction Following Not comparable

DeepSeek-V3.1-Terminus: 74.0 (#106), Devstral Small 2505: —

BenchmarkDeepSeek-V3.1-TerminusDevstral Small 2505
LMArena Instruction Following1404—

Long Context Not comparable

DeepSeek-V3.1-Terminus: 43.4 (#97), Devstral Small 2505: —

BenchmarkDeepSeek-V3.1-TerminusDevstral Small 2505
LMArena Longer Query1421—

Writing & Preference Not comparable

DeepSeek-V3.1-Terminus: 61.0 (#92), Devstral Small 2505: —

BenchmarkDeepSeek-V3.1-TerminusDevstral Small 2505
LMArena Text1419—
LMArena Creative Writing1403—
LMArena Multi-Turn1411—

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Devstral Small 2505?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.0× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

Which is cheaper, DeepSeek-V3.1-Terminus or Devstral Small 2505?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.27 and $1.

Is DeepSeek-V3.1-Terminus or Devstral Small 2505 better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.

How many benchmarks do DeepSeek-V3.1-Terminus and Devstral Small 2505 share?

3 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Devstral Small 2505 has 4.

Related comparisons

Go deeper