Model comparison

DeepSeek-V3.1-Terminus vs Mistral Small 3.2

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 30.8 on the Noometry Index. Mistral Small 3.2 costs 3.6× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

Last verified October 10, 2026. 1 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

42.6

Rank #96 Confirmed

Mistral Small 3.2

Mistral AI

30.8

Rank #271 Confirmed

Summary

They share 1 benchmark with published results for both. DeepSeek-V3.1-Terminus scores higher in 3 categories and Mistral Small 3.2 in 0 categories; 3 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 45.1.
The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 40.4% for Mistral Small 3.2.
Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
Mistral Small 3.2 accepts more context: 256K tokens versus 164K.

Side by side

DeepSeek-V3.1-Terminus and Mistral Small 3.2 specifications
	DeepSeek-V3.1-Terminus	Mistral Small 3.2
Provider	DeepSeek	Mistral AI
Noometry Index	42.6	30.8
Released	2025-09-22	2025-06-20
Weights	Open	Open
Context window	164K	256K
Max output	66K	16K
Input $ / M tokens	$0.30	$0.0938
Output $ / M tokens	$1	$0.25
Results tracked	16	6

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

Category by category

Coding Not comparable

DeepSeek-V3.1-Terminus: 41.5 (#114), Mistral Small 3.2: —

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
SciCode	40.6%	—
LMArena Coding	1426	—
ALE-Bench	745.17	—

Reasoning DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 25.7 (#126), Mistral Small 3.2: 17.5 (#282)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
Kagi LLM Benchmark	57.4%	40.4%
CritPt	1.7%	—
Chess Puzzles	—	1%
LMArena Hard Prompts	1427	—
DTBench	81.3%	—
LMCA	28.6%	—
Epoch Capabilities Index	—	131.73

Math DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 35.7 (#138), Mistral Small 3.2: 24.9 (#251)

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
OTIS Mock AIME 2024-2025	—	30.3%
LMArena Math	1402	—

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Mistral Small 3.2: 26.8 (#249)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
GPQA Diamond	—	49.1%

Multilingual Not comparable

DeepSeek-V3.1-Terminus: 52.3 (#87), Mistral Small 3.2: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
LMArena Non-English	1407	—
LMArena Russian	1434	—

Instruction Following Not comparable

DeepSeek-V3.1-Terminus: 74.4 (#96), Mistral Small 3.2: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
LMArena Instruction Following	1406	—

Long Context Not comparable

DeepSeek-V3.1-Terminus: 43.5 (#88), Mistral Small 3.2: —

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
LMArena Longer Query	1426	—

Writing & Preference DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 61.3 (#87), Mistral Small 3.2: 45.1 (#219)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Mistral Small 3.2
LMArena Text	1420	—
LMArena Creative Writing	1404	—
EQ-Bench Creative Writing	—	1255
LMArena Multi-Turn	1411	—

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Mistral Small 3.2?

Which is cheaper, DeepSeek-V3.1-Terminus or Mistral Small 3.2?

Mistral Small 3.2 is cheaper. It lists at $0.0938 per million input tokens and $0.25 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.

Which has the bigger context window?

Mistral Small 3.2 does, with 256K tokens against 164K.

How many benchmarks do DeepSeek-V3.1-Terminus and Mistral Small 3.2 share?

1 benchmark has published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Mistral Small 3.2 has 6.