Model comparison

Devstral Small 2505 vs Mixtral 8x7B

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 26.8 on the Noometry Index.

Last verified . 0 shared benchmarks.

Devstral Small 2505 Mistral AI

33.9

Rank #228 Reported

Mixtral 8x7B Mistral AI

26.8

Rank #328 Confirmed

Summary

  • The widest gap is in coding, where Devstral Small 2505 leads 38.6 to 32.2.
  • Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
  • Devstral Small 2505 accepts more context: 128K tokens versus 32K.

Side by side

Devstral Small 2505 and Mixtral 8x7B specifications
Devstral Small 2505Mixtral 8x7B
ProviderMistral AIMistral AI
Noometry Index33.926.8
Released2025-05-072023-12-11
WeightsOpenOpen
Context window128K32K
Max output128K32K
Input $ / M tokens$0.10$0.70
Output $ / M tokens$0.30$0.70
Results tracked438

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

Category by category

Coding Devstral Small 2505 leads

Devstral Small 2505: 38.6 (#160), Mixtral 8x7B: 32.2 (#265)

Coding benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
SWE-bench Verified (bash only)56.4%—
SciCode28.8%—
LMArena Coding—1127
HumanEval+—39.6%
MBPP+—49.7%

Reasoning Devstral Small 2505 leads

Devstral Small 2505: 19.1 (#243), Mixtral 8x7B: 17.4 (#283)

Reasoning benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
Kagi LLM Benchmark37.7%—
CritPt0%—
LMArena Hard Prompts—1115
DTBench—49.6%
Adversarial NLI—55.2%
Epoch Capabilities Index—118.38
ForecastBench—56.3
HellaSwag—86.7%
PIQA—83.6%
WinoGrande—77.2%

Math Not comparable

Devstral Small 2505: —, Mixtral 8x7B: 17.2 (#284)

Math benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
Omni-MATH—10.5%
LMArena Math—1147
MATH Level 5—10%
GSM8K—74.4%

Knowledge Not comparable

Devstral Small 2505: —, Mixtral 8x7B: 11.0 (#296)

Knowledge benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
GPQA Diamond—30.6%
MMLU-Pro—33.5%
GPQA (HELM)—29.6%
LMArena Expert—1088
ARC (AI2) Challenge—87.3%
MMLU—70.6%
OpenBookQA—85.8%
TriviaQA—82.2%

Multilingual Not comparable

Devstral Small 2505: —, Mixtral 8x7B: 29.8 (#261)

Multilingual benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
LMArena Non-English—1077
LMArena Chinese—1055
LMArena French—1165
LMArena German—1114
LMArena Japanese—931
LMArena Korean—968
LMArena Russian—1090
LMArena Spanish—1110

Instruction Following Not comparable

Devstral Small 2505: —, Mixtral 8x7B: 51.2 (#292)

Instruction Following benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
IFEval—57.5%
LMArena Instruction Following—1110

Long Context Not comparable

Devstral Small 2505: —, Mixtral 8x7B: 33.4 (#255)

Long Context benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
LMArena Longer Query—1103

Writing & Preference Not comparable

Devstral Small 2505: —, Mixtral 8x7B: 34.4 (#265)

Writing & Preference benchmarks
BenchmarkDevstral Small 2505Mixtral 8x7B
LMArena Text—1132
LMArena Creative Writing—1109
WildBench—67.3%
LMArena Multi-Turn—1115

Frequently asked questions

Is Devstral Small 2505 better than Mixtral 8x7B?

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 26.8 on the Noometry Index.

Which is cheaper, Devstral Small 2505 or Mixtral 8x7B?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.

Is Devstral Small 2505 or Mixtral 8x7B better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 32.2 in the Noometry coding category.

Which has the bigger context window?

Devstral Small 2505 does, with 128K tokens against 32K.

How many benchmarks do Devstral Small 2505 and Mixtral 8x7B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Mixtral 8x7B has 38.

Related comparisons

Go deeper