Model comparison

Devstral Small 2505 vs Llama 3.2 1B

Devstral Small 2505 is the stronger model overall, scoring 34.3 to 20.1 on the Noometry Index. Llama 3.2 1B costs 2.1× less per token, which makes it the better buy when Devstral Small 2505's lead doesn't matter for your workload.

Last verified October 11, 2026. 0 shared benchmarks.

Devstral Small 2505

Mistral AI

34.3

Rank #233 Reported

Llama 3.2 1B

Summary

The widest gap is in coding, where Devstral Small 2505 leads 38.9 to 21.1.
Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.10 / $0.30 for Devstral Small 2505.
Devstral Small 2505 accepts more context: 128K tokens versus 60K.

Side by side

Devstral Small 2505 and Llama 3.2 1B specifications
	Devstral Small 2505	Llama 3.2 1B
Provider	Mistral AI	Meta
Noometry Index	34.3	20.1
Released	2025-05-07	2024-09-24
Weights	Open	Open
Context window	128K	60K
Max output	128K	54K
Input $ / M tokens	$0.10	$0.027
Output $ / M tokens	$0.30	$0.20
Results tracked	4	22

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

Category by category

Coding Devstral Small 2505 leads

Devstral Small 2505: 38.9 (#166), Llama 3.2 1B: 21.1 (#338)

Coding benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
SWE-bench Verified (bash only)	56.4%	—
SciCode	28.8%	—
BigCodeBench Instruct	—	8.2%
LMArena Coding	—	1070
BigCodeBench Complete	—	11.3%

Agentic & Tool Use Not comparable

Devstral Small 2505: —, Llama 3.2 1B: 14.6 (#150)

Agentic & Tool Use benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
Berkeley Function Calling Leaderboard	—	10.8%
BALROG	—	6.6%

Reasoning Devstral Small 2505 leads

Devstral Small 2505: 19.7 (#252), Llama 3.2 1B: 16.2 (#308)

Reasoning benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
Kagi LLM Benchmark	37.7%	—
CritPt	0%	—
Chess Puzzles	—	0%
LMArena Hard Prompts	—	1044
Epoch Capabilities Index	—	101.99

Math Not comparable

Devstral Small 2505: —, Llama 3.2 1B: 10.4 (#313)

Math benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
OTIS Mock AIME 2024-2025	—	0.6%
LMArena Math	—	1086

Knowledge Not comparable

Devstral Small 2505: —, Llama 3.2 1B: 7.2 (#312)

Knowledge benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
GPQA Diamond	—	23.9%
LMArena Expert	—	1007

Multilingual Not comparable

Devstral Small 2505: —, Llama 3.2 1B: 23.8 (#292)

Multilingual benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
LMArena Non-English	—	973
LMArena Chinese	—	959
LMArena German	—	1014
LMArena Russian	—	941

Instruction Following Not comparable

Devstral Small 2505: —, Llama 3.2 1B: 52.4 (#290)

Instruction Following benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
LMArena Instruction Following	—	1031

Long Context Not comparable

Devstral Small 2505: —, Llama 3.2 1B: 31.9 (#274)

Long Context benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
LMArena Longer Query	—	1050

Writing & Preference Not comparable

Devstral Small 2505: —, Llama 3.2 1B: 21.3 (#310)

Writing & Preference benchmarks
Benchmark	Devstral Small 2505	Llama 3.2 1B
LMArena Text	—	1055
LMArena Creative Writing	—	1033
EQ-Bench Creative Writing	—	200
LMArena Multi-Turn	—	1030

Frequently asked questions

Is Devstral Small 2505 better than Llama 3.2 1B?

Which is cheaper, Devstral Small 2505 or Llama 3.2 1B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Devstral Small 2505 lists at $0.10 and $0.30.

Is Devstral Small 2505 or Llama 3.2 1B better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 21.1 in the Noometry coding category.

Which has the bigger context window?

Devstral Small 2505 does, with 128K tokens against 60K.

How many benchmarks do Devstral Small 2505 and Llama 3.2 1B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Llama 3.2 1B has 22.