Model comparison

Mistral Medium 3.5 vs Trinity Large Thinking

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 38.6 on the Noometry Index. Trinity Large Thinking costs 7.7× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

Last verified October 10, 2026. 18 shared benchmarks.

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Trinity Large Thinking

Arcee AI

38.6

Rank #185 Confirmed

Summary

They share 18 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 7 categories and Trinity Large Thinking in 1 category; 6 gaps are clear of the uncertainty.
The widest gap is in multilingual, where Mistral Medium 3.5 leads 51.9 to 46.2.
Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.

Side by side

Mistral Medium 3.5 and Trinity Large Thinking specifications
	Mistral Medium 3.5	Trinity Large Thinking
Provider	Mistral AI	Arcee AI
Noometry Index	40.2	38.6
Released	—	2026-04-01
Weights	Open	Open
Context window	262K	262K
Max output	210K	80K
Input $ / M tokens	$1.50	$0.25
Output $ / M tokens	$7.50	$0.80
Results tracked	22	24

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

Category by category

Coding Mistral Medium 3.5 leads

Mistral Medium 3.5: 36.0 (#213), Trinity Large Thinking: 34.1 (#244)

Coding benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena WebDev	1264	1238
LMArena Coding	1461	1381
SciCode	—	36.1%

Reasoning Too close to call

Mistral Medium 3.5: 17.3 (#295), Trinity Large Thinking: 16.9 (#298)

Reasoning benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
NYT Connections (extended)	12.9%	16.5%
LMArena Hard Prompts	1436	1350
Kagi LLM Benchmark	41.4%	—
CritPt	—	0.9%
Thematic Generalization	—	41.6%
Surface Evolver Bench	—	15.6%
Epoch Capabilities Index	141.35	—

Math Mistral Medium 3.5 leads

Mistral Medium 3.5: 39.1 (#113), Trinity Large Thinking: 37.6 (#149)

Math benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena Math	1431	1366

Knowledge Too close to call

Mistral Medium 3.5: 40.0 (#126), Trinity Large Thinking: 40.9 (#113)

Knowledge benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena Expert	1432	1360
Vectara Hallucination Rate	—	6.9%

Multimodal Not comparable

Mistral Medium 3.5: 38.3 (#65), Trinity Large Thinking: —

Multimodal benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena Vision	1223	—

Multilingual Mistral Medium 3.5 leads

Mistral Medium 3.5: 51.9 (#100), Trinity Large Thinking: 46.2 (#160)

Multilingual benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena Non-English	1404	1325
LMArena Chinese	1442	1373
LMArena French	1448	1374
LMArena German	1451	1356
LMArena Korean	1385	1306
LMArena Russian	1395	1337
LMArena Spanish	1409	1357
LMArena Japanese	—	1311

Instruction Following Mistral Medium 3.5 leads

Mistral Medium 3.5: 74.6 (#90), Trinity Large Thinking: 70.5 (#162)

Instruction Following benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena Instruction Following	1415	1334

Long Context Mistral Medium 3.5 leads

Mistral Medium 3.5: 43.2 (#103), Trinity Large Thinking: 41.3 (#144)

Long Context benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena Longer Query	1415	1355

Writing & Preference Mistral Medium 3.5 leads

Mistral Medium 3.5: 58.5 (#117), Trinity Large Thinking: 53.8 (#158)

Writing & Preference benchmarks
Benchmark	Mistral Medium 3.5	Trinity Large Thinking
LMArena Text	1421	1340
LMArena Creative Writing	1374	1320
LMArena Multi-Turn	1423	1342
EQ-Bench 4	993	—

Frequently asked questions

Is Mistral Medium 3.5 better than Trinity Large Thinking?

Which is cheaper, Mistral Medium 3.5 or Trinity Large Thinking?

Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Mistral Medium 3.5 or Trinity Large Thinking better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Mistral Medium 3.5 and Trinity Large Thinking share?

18 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Trinity Large Thinking has 24.