Model comparison

GPT-5.2 Pro vs Mistral Medium 3.5

GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 39.6 on the Noometry Index. Mistral Medium 3.5 costs 19× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

Last verified October 10, 2026. 2 shared benchmarks.

GPT-5.2 Pro OpenAI

52.2

Rank #34 Reported

Mistral Medium 3.5

Mistral AI

39.6

Rank #151 Confirmed

Summary

They share 2 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and Mistral Medium 3.5 in 0 categories; 2 gaps are clear of the uncertainty.
The widest gap is in reasoning, where GPT-5.2 Pro leads 51.8 to 16.6.
The biggest single-benchmark swing is NYT Connections (extended): 79.3% for GPT-5.2 Pro and 12.9% for Mistral Medium 3.5.
Mistral Medium 3.5 is cheaper at $1.50 / $7.50 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
GPT-5.2 Pro accepts more context: 400K tokens versus 262K.
Mistral Medium 3.5 has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 Pro and Mistral Medium 3.5 specifications
	GPT-5.2 Pro	Mistral Medium 3.5
Provider	OpenAI	Mistral AI
Noometry Index	52.2	39.6
Released	2025-12-11	—
Weights	Proprietary	Open
Context window	400K	262K
Max output	128K	210K
Input $ / M tokens	$21	$1.50
Output $ / M tokens	$168	$7.50
Results tracked	8	22

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

Category by category

Coding Not comparable

GPT-5.2 Pro: —, Mistral Medium 3.5: 35.7 (#208)

Coding benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
LMArena WebDev	—	1263
LMArena Coding	—	1461

Reasoning GPT-5.2 Pro leads

GPT-5.2 Pro: 51.8 (#31), Mistral Medium 3.5: 16.6 (#290)

Reasoning benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
NYT Connections (extended)	79.3%	12.9%
Epoch Capabilities Index	155.41	141.42
ARC-AGI-2	54.2%	—
SimpleBench	57.4%	—
Kagi LLM Benchmark	—	41.4%
ARC-AGI-1	90.5%	—
LMArena Hard Prompts	—	1436

Math GPT-5.2 Pro leads

GPT-5.2 Pro: 64.8 (#23), Mistral Medium 3.5: 36.4 (#113)

Math benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
FrontierMath (Tiers 1-3)	74%	—
FrontierMath Tier 4	46%	—
LMArena Math	—	1432
FrontierMath Tier 4 (v1)	31.3%	—

Knowledge Not comparable

GPT-5.2 Pro: —, Mistral Medium 3.5: 39.3 (#123)

Knowledge benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
LMArena Expert	—	1431

Multimodal Not comparable

GPT-5.2 Pro: —, Mistral Medium 3.5: 37.6 (#64)

Multimodal benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
LMArena Vision	—	1222

Multilingual Not comparable

GPT-5.2 Pro: —, Mistral Medium 3.5: 52.1 (#93)

Multilingual benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
LMArena Non-English	—	1405
LMArena Chinese	—	1443
LMArena French	—	1448
LMArena German	—	1453
LMArena Korean	—	1387
LMArena Russian	—	1396
LMArena Spanish	—	1406

Instruction Following Not comparable

GPT-5.2 Pro: —, Mistral Medium 3.5: 74.7 (#87)

Instruction Following benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
LMArena Instruction Following	—	1414

Long Context Not comparable

GPT-5.2 Pro: —, Mistral Medium 3.5: 43.2 (#101)

Long Context benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
LMArena Longer Query	—	1414

Writing & Preference Not comparable

GPT-5.2 Pro: —, Mistral Medium 3.5: 58.6 (#113)

Writing & Preference benchmarks
Benchmark	GPT-5.2 Pro	Mistral Medium 3.5
LMArena Text	—	1421
LMArena Creative Writing	—	1372
EQ-Bench 4	—	993
LMArena Multi-Turn	—	1423

Frequently asked questions

Is GPT-5.2 Pro better than Mistral Medium 3.5?

Which is cheaper, GPT-5.2 Pro 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; GPT-5.2 Pro lists at $21 and $168.

Which has the bigger context window?

GPT-5.2 Pro does, with 400K tokens against 262K.

How many benchmarks do GPT-5.2 Pro and Mistral Medium 3.5 share?

2 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Mistral Medium 3.5 has 22.