Model comparison

Devstral Small 2505 vs Granite 4.2 8B

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 34.3 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Devstral Small 2505

Mistral AI

34.3

Rank #233 Reported

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

Summary

The widest gap is in reasoning, where Granite 4.2 8B leads 26.6 to 19.7.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.10 / $0.30 for Devstral Small 2505.
Granite 4.2 8B accepts more context: 131K tokens versus 128K.

Side by side

Devstral Small 2505 and Granite 4.2 8B specifications
	Devstral Small 2505	Granite 4.2 8B
Provider	Mistral AI	IBM
Noometry Index	34.3	40.5
Released	2025-05-07	—
Weights	Open	Open
Context window	128K	131K
Max output	128K	118K
Input $ / M tokens	$0.10	$0.06
Output $ / M tokens	$0.30	$0.25
Results tracked	4	11

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

Category by category

Coding Granite 4.2 8B leads

Devstral Small 2505: 38.9 (#166), Granite 4.2 8B: 40.5 (#137)

Coding benchmarks
Benchmark	Devstral Small 2505	Granite 4.2 8B
SWE-bench Verified (bash only)	56.4%	—
SciCode	28.8%	—
LMArena Coding	—	1380

Reasoning Granite 4.2 8B leads

Devstral Small 2505: 19.7 (#252), Granite 4.2 8B: 26.6 (#131)

Reasoning benchmarks
Benchmark	Devstral Small 2505	Granite 4.2 8B
Kagi LLM Benchmark	37.7%	—
CritPt	0%	—
LMArena Hard Prompts	—	1329

Knowledge Not comparable

Devstral Small 2505: —, Granite 4.2 8B: 38.4 (#145)

Knowledge benchmarks
Benchmark	Devstral Small 2505	Granite 4.2 8B
LMArena Expert	—	1384

Multilingual Not comparable

Devstral Small 2505: —, Granite 4.2 8B: 44.5 (#178)

Multilingual benchmarks
Benchmark	Devstral Small 2505	Granite 4.2 8B
LMArena Non-English	—	1302
LMArena Chinese	—	1366
LMArena Russian	—	1285

Instruction Following Not comparable

Devstral Small 2505: —, Granite 4.2 8B: 68.7 (#184)

Instruction Following benchmarks
Benchmark	Devstral Small 2505	Granite 4.2 8B
LMArena Instruction Following	—	1301

Long Context Not comparable

Devstral Small 2505: —, Granite 4.2 8B: 40.3 (#159)

Long Context benchmarks
Benchmark	Devstral Small 2505	Granite 4.2 8B
LMArena Longer Query	—	1324

Writing & Preference Not comparable

Devstral Small 2505: —, Granite 4.2 8B: 49.6 (#189)

Writing & Preference benchmarks
Benchmark	Devstral Small 2505	Granite 4.2 8B
LMArena Text	—	1320
LMArena Creative Writing	—	1236
LMArena Multi-Turn	—	1301

Frequently asked questions

Is Devstral Small 2505 better than Granite 4.2 8B?

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 34.3 on the Noometry Index.

Which is cheaper, Devstral Small 2505 or Granite 4.2 8B?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Devstral Small 2505 lists at $0.10 and $0.30.

Is Devstral Small 2505 or Granite 4.2 8B better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

Granite 4.2 8B does, with 131K tokens against 128K.

How many benchmarks do Devstral Small 2505 and Granite 4.2 8B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Granite 4.2 8B has 11.