Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 Terminus vs Mistral Small 3

DeepSeek V3.1 Terminus leads Mistral Small 3 on the Artificial Analysis Intelligence Index, 14.8 to 6.7, and Mistral Small 3 costs 12.7x less per output token ($0.08 vs $1.0142 per million). Updated October 22, 2026; 29 benchmarks have a result for both.

Replace DeepSeek V3.1 Terminus Replace Mistral Small 3
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
No data
Output $/M
$1.0142
29
Mistral Small 3Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.08
0
vs boards won of 29 shared

DeepSeek V3.1 Terminus or Mistral Small 3: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick DeepSeek V3.1 Terminus for a larger context window (164K against 33K tokens).

Model ADeepSeek V3.1 TerminusDeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Small 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
29
DeepSeek V3.1 Terminus only
16
Mistral Small 3 only
7
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
DeepSeek V3.1 Terminus not benchmarked, Mistral Small 3 not benchmarked.
Widest category
Math, 65.9 points apart on average over 3 shared benchmarks.
Widest single gap
AA Math Index: DeepSeek V3.1 Terminus 89.7 against Mistral Small 3 4.3, 85.4 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 Terminus $1.0142 against Mistral Small 3 $0.08 per million output tokens, 12.7x apart.
Context window
DeepSeek V3.1 Terminus takes 164K tokens, Mistral Small 3 33K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryDeepSeek V3.1 TerminusBarsMistral Small 3Ties
Coding30
Intelligence10
Agentic work10
Reasoning40
Math30
Knowledge50
General120
All shared boards290
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
AA Coding Index43.5Not measuredOnly DeepSeek V3.1 Terminus measured
LiveCodeBench (Artificial Analysis run)79.8%25.2%DeepSeek V3.1 Terminus
SciCode38.0%Not measuredOnly DeepSeek V3.1 Terminus measured
Terminal-Bench Hard (Artificial Analysis run)31.8%Not measuredOnly DeepSeek V3.1 Terminus measured
ALE-Bench745.2Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: coding14251246DeepSeek V3.1 Terminus
LMArena Text: software and IT14261248DeepSeek V3.1 Terminus
Neither model has a result on the other 32 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
AA Intelligence Index14.86.7DeepSeek V3.1 Terminus
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
AA Agentic Index6.8Not measuredOnly DeepSeek V3.1 Terminus measured
τ²-Bench Telecom37.1%19.6%DeepSeek V3.1 Terminus
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
GPQA Diamond (Artificial Analysis run)79.2%46.2%DeepSeek V3.1 Terminus
Humanity's Last Exam (Artificial Analysis run)16.4%3.8%DeepSeek V3.1 Terminus
LMArena Text: hard prompts14261233DeepSeek V3.1 Terminus
LMArena Text: expertNot measured1202Only Mistral Small 3 measured
LMArena Text: hard prompts in English14321243DeepSeek V3.1 Terminus
Kagi LLM Benchmark57.4%Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
AA Math Index89.74.3DeepSeek V3.1 Terminus
AIME 2025 (Artificial Analysis run)89.7%4.3%DeepSeek V3.1 Terminus
LMArena Text: math14021240DeepSeek V3.1 Terminus
LMArena Text: mathematical workNot measured1243Only Mistral Small 3 measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
MMLU Pro (Artificial Analysis run)85.1%65.2%DeepSeek V3.1 Terminus
LMArena Text: science14511235DeepSeek V3.1 Terminus
LMArena Text: medicine and healthcare14681215DeepSeek V3.1 Terminus
LMArena Text: legal and government14571219DeepSeek V3.1 Terminus
LMArena Text: business and finance14141205DeepSeek V3.1 Terminus
Neither model has a result on the other 13 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
Design Arena: websites1187Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: UI components1182Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: game dev1131Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: data viz1168Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: 3D1141Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: all code categories1175Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: SVG1065Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
General benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
IFBench57.0%26.4%DeepSeek V3.1 Terminus
Long context reasoning (AA-LCR)69.3%0.0%DeepSeek V3.1 Terminus
DTBench81.3%Not measuredOnly DeepSeek V3.1 Terminus measured
LMCA28.6%Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text14191234DeepSeek V3.1 Terminus
LMArena Text: instruction following14041214DeepSeek V3.1 Terminus
LMArena Text: creative writing14031194DeepSeek V3.1 Terminus
LMArena Text: English14291256DeepSeek V3.1 Terminus
LMArena Text: non-English14081198DeepSeek V3.1 Terminus
LMArena Text: ChineseNot measured1204Only Mistral Small 3 measured
LMArena Text: GermanNot measured1211Only Mistral Small 3 measured
LMArena Text: JapaneseNot measured1111Only Mistral Small 3 measured
LMArena Text: KoreanNot measured1188Only Mistral Small 3 measured
LMArena Text: FrenchNot measured1204Only Mistral Small 3 measured
LMArena Text: Russian14351216DeepSeek V3.1 Terminus
LMArena Text: Polish1427Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: multi-turn14111217DeepSeek V3.1 Terminus
LMArena Text: longer queries14221246DeepSeek V3.1 Terminus
LMArena Text: writing and language14091214DeepSeek V3.1 Terminus
LMArena Text: entertainment and media13911184DeepSeek V3.1 Terminus
Neither model has a result on the other 26 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.1 Terminus and Mistral Small 3
BenchmarkDeepSeek V3.1 TerminusMistral Small 3Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

DeepSeek V3.1 Terminus$0.0008Fits in one request
Mistral Small 3$0.0001Fits in one request

Mistral Small 3 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1 Terminus$0.018Fits in one request
Mistral Small 3$0.0027Exceeds the context window

Mistral Small 3 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1 Terminus$0.071Exceeds the context window
Mistral Small 3$0.011Exceeds the context window

Mistral Small 3 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of DeepSeek V3.1 Terminus and Mistral Small 3
SpecificationDeepSeek V3.1 TerminusMistral Small 3
MakerDeepSeekMistral AI
WeightsOpen weightsOpen weights
ReleasedSeptember 22, 2025January 30, 2025
Context window164K33K
Input $/Mtok$0.3063$0.05
Output $/Mtok$1.0142$0.08
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 Terminus better than Mistral Small 3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for a larger context window (164K against 33K tokens).

Which is cheaper, DeepSeek V3.1 Terminus or Mistral Small 3?

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; Mistral Small 3 costs $0.05 and $0.08. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.1 Terminus or Mistral Small 3?

DeepSeek V3.1 Terminus, with 164K tokens against 33K.

How many benchmarks is the DeepSeek V3.1 Terminus vs Mistral Small 3 comparison based on?

29 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 independent benchmarks and Mistral Small 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next