Model comparison

Mistral Medium vs Mistral Medium 3.5

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 36.3 on the Noometry Index.

Last verified October 10, 2026. 18 shared benchmarks.

Mistral Medium

Mistral AI

36.3

Rank #218 Confirmed

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Summary

They share 18 benchmarks with published results for both. Mistral Medium scores higher in 3 categories and Mistral Medium 3.5 in 6 categories; 6 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Mistral Medium 3.5 leads 40.0 to 25.0.
The biggest single-benchmark swing is Kagi LLM Benchmark: 50% for Mistral Medium and 41.4% for Mistral Medium 3.5.
Both cost about the same: $1.50 input and $7.50 output per million tokens.

Side by side

Mistral Medium and Mistral Medium 3.5 specifications
	Mistral Medium	Mistral Medium 3.5
Provider	Mistral AI	Mistral AI
Noometry Index	36.3	40.2
Released	2023-12-11	—
Weights	Open	Open
Context window	262K	262K
Max output	262K	210K
Input $ / M tokens	$1.50	$1.50
Output $ / M tokens	$7.50	$7.50
Results tracked	36	22

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

Category by category

Coding Mistral Medium 3.5 leads

Mistral Medium: 34.2 (#243), Mistral Medium 3.5: 36.0 (#213)

Coding benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Coding	1434	1461
FrontierCode	8%	—
LMArena WebDev	—	1264
SciCode	40.2%	—
WeirdML	43.7%	—
ALE-Bench	763.98	—

Agentic & Tool Use Not comparable

Mistral Medium: 28.3 (#90), Mistral Medium 3.5: —

Agentic & Tool Use benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
Berkeley Function Calling Leaderboard	37.7%	—

Reasoning Mistral Medium leads

Mistral Medium: 24.0 (#167), Mistral Medium 3.5: 17.3 (#295)

Reasoning benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
Kagi LLM Benchmark	50%	41.4%
LMArena Hard Prompts	1426	1436
NYT Connections (extended)	—	12.9%
CritPt	0%	—
DTBench	75.5%	—
LMCA	26.1%	—
Surface Evolver Bench	26.9%	—
Epoch Capabilities Index	—	141.35

Math Mistral Medium 3.5 leads

Mistral Medium: 28.1 (#245), Mistral Medium 3.5: 39.1 (#113)

Math benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Math	1408	1431
OTIS Mock AIME 2024-2025	32.2%	—
ProofBench	9%	—
MATH Level 5	81.6%	—
FrontierMath (Feb 2025 set)	0.3%	—

Knowledge Mistral Medium 3.5 leads

Mistral Medium: 25.0 (#265), Mistral Medium 3.5: 40.0 (#126)

Knowledge benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Expert	1408	1432
GPQA Diamond	59.5%	—
Humanity's Last Exam	4.5%	—
Vectara Hallucination Rate	22.7%	—

Multimodal Mistral Medium 3.5 leads

Mistral Medium: 35.3 (#88), Mistral Medium 3.5: 38.3 (#65)

Multimodal benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Vision	1172	1223

Multilingual Too close to call

Mistral Medium: 52.1 (#91), Mistral Medium 3.5: 51.9 (#100)

Multilingual benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Non-English	1408	1404
LMArena Chinese	1447	1442
LMArena French	1459	1448
LMArena German	1432	1451
LMArena Korean	1380	1385
LMArena Russian	1411	1395
LMArena Spanish	1433	1409
LMArena Japanese	1378	—

Instruction Following Too close to call

Mistral Medium: 73.7 (#116), Mistral Medium 3.5: 74.6 (#90)

Instruction Following benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Instruction Following	1398	1415

Long Context Too close to call

Mistral Medium: 42.9 (#114), Mistral Medium 3.5: 43.2 (#103)

Long Context benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Longer Query	1406	1415

Writing & Preference Mistral Medium leads

Mistral Medium: 60.0 (#103), Mistral Medium 3.5: 58.5 (#117)

Writing & Preference benchmarks
Benchmark	Mistral Medium	Mistral Medium 3.5
LMArena Text	1424	1421
LMArena Creative Writing	1391	1374
LMArena Multi-Turn	1418	1423
Short-Story Creative Writing	77.3%	—
EQ-Bench 4	—	993

Frequently asked questions

Is Mistral Medium better than Mistral Medium 3.5?

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 36.3 on the Noometry Index.

Which is cheaper, Mistral Medium or Mistral Medium 3.5?

Mistral Medium 3.5 is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

Is Mistral Medium or Mistral Medium 3.5 better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 34.2 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Mistral Medium and Mistral Medium 3.5 share?

18 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Mistral Medium 3.5 has 22.