Noometry

Model comparison

DeepSeek-V3.1-Terminus vs Magistral Small

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.9 on the Noometry Index.

Last verified . 4 shared benchmarks.

DeepSeek-V3.1-Terminus DeepSeek

42.6

Rank #96 Confirmed

Magistral Small Mistral AI

29.9

Rank #289 Confirmed

Summary

  • They share 4 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 3 categories and Magistral Small in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 25.7 to 6.9.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 6.3% for Magistral Small.
  • DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
  • DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.

Side by side

DeepSeek-V3.1-TerminusMagistral Small
ProviderDeepSeekMistral AI
Noometry Index42.629.9
Released2025-09-222025-06-10
WeightsOpenOpen
Context window164K128K
Max output66K40K
Input $ / M tokens$0.30$0.50
Output $ / M tokens$1$1.50
Results tracked1610

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: 41.5 (#114), Magistral Small: 37.8 (#172)

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
SciCode40.6%35.2%
LMArena Coding1426—
ALE-Bench745.17—

Reasoning DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 25.7 (#126), Magistral Small: 6.9 (#345)

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
Kagi LLM Benchmark57.4%6.3%
CritPt1.7%0.3%
DTBench81.3%61.3%
ARC-AGI-2—0%
ARC-AGI-1—5%
Chess Puzzles—3%
LMArena Hard Prompts1427—
LMCA28.6%—
Epoch Capabilities Index—133.19

Math DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 35.7 (#138), Magistral Small: 24.9 (#253)

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
OTIS Mock AIME 2024-2025—30%
LMArena Math1402—

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Magistral Small: 30.9 (#215)

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
GPQA Diamond—56.1%

Multilingual Not comparable

DeepSeek-V3.1-Terminus: 52.3 (#87), Magistral Small: —

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
LMArena Non-English1407—
LMArena Russian1434—

Instruction Following Not comparable

DeepSeek-V3.1-Terminus: 74.4 (#96), Magistral Small: —

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
LMArena Instruction Following1406—

Long Context Not comparable

DeepSeek-V3.1-Terminus: 43.5 (#88), Magistral Small: —

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
LMArena Longer Query1426—

Writing & Preference Not comparable

DeepSeek-V3.1-Terminus: 61.3 (#87), Magistral Small: —

BenchmarkDeepSeek-V3.1-TerminusMagistral Small
LMArena Text1420—
LMArena Creative Writing1404—
LMArena Multi-Turn1411—

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Magistral Small?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.9 on the Noometry Index.

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

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Magistral Small lists at $0.50 and $1.50.

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

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 37.8 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 Magistral Small share?

4 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Magistral Small has 10.

Related comparisons

Go deeper