Model comparison

DeepSeek-V3 vs Mistral Medium 3.5

DeepSeek-V3 and Mistral Medium 3.5 score almost the same on the Noometry Index (39.5 vs 40.2), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 18 shared benchmarks.

DeepSeek-V3

DeepSeek

39.5

Rank #166 Confirmed

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Summary

They share 18 benchmarks with published results for both. DeepSeek-V3 scores higher in 2 categories and Mistral Medium 3.5 in 6 categories; 8 gaps are clear of the uncertainty.
The widest gap is in long context, where Mistral Medium 3.5 leads 43.2 to 34.0.
The biggest single-benchmark swing is Kagi LLM Benchmark: 52.3% for DeepSeek-V3 and 41.4% for Mistral Medium 3.5.
DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
Mistral Medium 3.5 accepts more context: 262K tokens versus 164K.

Side by side

DeepSeek-V3 and Mistral Medium 3.5 specifications
	DeepSeek-V3	Mistral Medium 3.5
Provider	DeepSeek	Mistral AI
Noometry Index	39.5	40.2
Released	2024-12-26	—
Weights	Open	Open
Context window	164K	262K
Max output	164K	210K
Input $ / M tokens	$0.24	$1.50
Output $ / M tokens	$0.90	$7.50
Results tracked	60	22

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

Category by category

Coding DeepSeek-V3 leads

DeepSeek-V3: 42.3 (#106), Mistral Medium 3.5: 36.0 (#213)

Coding benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Coding	1368	1461
Aider Polyglot	55.1%	—
LMArena WebDev	—	1264
SciCode	35.8%	—
WeirdML	36.1%	—
BigCodeBench Instruct	50%	—
LiveBench Coding	70.9%	—
BigCodeBench Complete	62.2%	—
HumanEval+	86.6%	—
MBPP+	73%	—

Agentic & Tool Use Not comparable

DeepSeek-V3: —, Mistral Medium 3.5: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
METR Time Horizons	49.6%	—

Reasoning DeepSeek-V3 leads

DeepSeek-V3: 20.5 (#236), Mistral Medium 3.5: 17.3 (#295)

Reasoning benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
Kagi LLM Benchmark	52.3%	41.4%
LMArena Hard Prompts	1365	1436
Epoch Capabilities Index	135.94	141.35
SimpleBench	27.2%	—
NYT Connections (extended)	—	12.9%
CritPt	0%	—
LiveBench Reasoning	65.8%	—
DTBench	64.8%	—
LiveBench Data Analysis	60.9%	—
LMCA	15.5%	—
BIG-Bench Hard	87.5%	—
ForecastBench	59.1	—
HellaSwag	88.9%	—
LiveBench	66.9%	—
PIQA	84.7%	—
WinoGrande	85.2%	—

Math Mistral Medium 3.5 leads

DeepSeek-V3: 32.1 (#219), Mistral Medium 3.5: 39.1 (#113)

Math benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Math	1373	1431
OTIS Mock AIME 2024-2025	37.8%	—
Omni-MATH	40.3%	—
LiveBench Math	73.5%	—
MATH Level 5	75.5%	—
FrontierMath (Feb 2025 set)	1.7%	—

Knowledge Mistral Medium 3.5 leads

DeepSeek-V3: 37.5 (#155), Mistral Medium 3.5: 40.0 (#126)

Knowledge benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Expert	1351	1432
GPQA Diamond	67.6%	—
MMLU-Pro	72.3%	—
Confabulations	26.1%	—
Vectara Hallucination Rate	6.1%	—
GPQA (HELM)	53.8%	—
ARC (AI2) Challenge	95.3%	—
MMLU	87.2%	—
TriviaQA	82.9%	—

Multimodal Not comparable

DeepSeek-V3: —, Mistral Medium 3.5: 38.3 (#65)

Multimodal benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Vision	—	1223

Multilingual Mistral Medium 3.5 leads

DeepSeek-V3: 48.5 (#143), Mistral Medium 3.5: 51.9 (#100)

Multilingual benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Non-English	1358	1404
LMArena Chinese	1391	1442
LMArena French	1385	1448
LMArena German	1374	1451
LMArena Korean	1319	1385
LMArena Russian	1373	1395
LMArena Spanish	1358	1409
LMArena Japanese	1333	—

Instruction Following Mistral Medium 3.5 leads

DeepSeek-V3: 72.8 (#130), Mistral Medium 3.5: 74.6 (#90)

Instruction Following benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Instruction Following	1345	1415
LiveBench Instruction Following	81.5%	—
IFEval	83.2%	—

Long Context Mistral Medium 3.5 leads

DeepSeek-V3: 34.0 (#253), Mistral Medium 3.5: 43.2 (#103)

Long Context benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Longer Query	1352	1415
Fiction.LiveBench	50%	—

Writing & Preference Mistral Medium 3.5 leads

DeepSeek-V3: 57.4 (#130), Mistral Medium 3.5: 58.5 (#117)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3	Mistral Medium 3.5
LMArena Text	1375	1421
LMArena Creative Writing	1364	1374
LMArena Multi-Turn	1389	1423
Short-Story Creative Writing	77%	—
EQ-Bench Creative Writing	1472	—
WildBench	83%	—
EQ-Bench 4	—	993
LiveBench Language	49.1%	—

Frequently asked questions

Is DeepSeek-V3 better than Mistral Medium 3.5?

DeepSeek-V3 and Mistral Medium 3.5 score almost the same on the Noometry Index (39.5 vs 40.2), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek-V3 or Mistral Medium 3.5?

DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is DeepSeek-V3 or Mistral Medium 3.5 better for coding?

DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 36.0 in the Noometry coding category.

Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 164K.

How many benchmarks do DeepSeek-V3 and Mistral Medium 3.5 share?

18 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Mistral Medium 3.5 has 22.