Model comparison

GPT-5.2 Pro vs Mistral Large 3

GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 38.6 on the Noometry Index. Mistral Large 3 costs 154× 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. 1 shared benchmarks.

GPT-5.2 Pro OpenAI

52.2

Rank #34 Reported

Mistral Large 3

Mistral AI

38.6

Rank #172 Confirmed

Summary

They share 1 benchmark with published results for both. GPT-5.2 Pro scores higher in 2 categories and Mistral Large 3 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 14.6.
The biggest single-benchmark swing is NYT Connections (extended): 79.3% for GPT-5.2 Pro and 7.5% for Mistral Large 3.
Mistral Large 3 is cheaper at $0.25 / $0.75 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 Large 3 has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 Pro and Mistral Large 3 specifications
	GPT-5.2 Pro	Mistral Large 3
Provider	OpenAI	Mistral AI
Noometry Index	52.2	38.6
Released	2025-12-11	2025-12-02
Weights	Proprietary	Open
Context window	400K	262K
Max output	128K	8K
Input $ / M tokens	$21	$0.25
Output $ / M tokens	$168	$0.75
Results tracked	8	24

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

Category by category

Coding Not comparable

GPT-5.2 Pro: —, Mistral Large 3: 34.1 (#230)

Coding benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
LMArena WebDev	—	1230
LMArena Coding	—	1447

Reasoning GPT-5.2 Pro leads

GPT-5.2 Pro: 51.8 (#31), Mistral Large 3: 14.6 (#314)

Reasoning benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
NYT Connections (extended)	79.3%	7.5%
ARC-AGI-2	54.2%	—
SimpleBench	57.4%	—
Kagi LLM Benchmark	—	50.9%
ARC-AGI-1	90.5%	—
Thematic Generalization	—	23%
LMArena Hard Prompts	—	1429
Epoch Capabilities Index	155.41	—

Math GPT-5.2 Pro leads

GPT-5.2 Pro: 64.8 (#23), Mistral Large 3: 36.0 (#131)

Math benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
FrontierMath (Tiers 1-3)	74%	—
FrontierMath Tier 4	46%	—
LMArena Math	—	1415
FrontierMath Tier 4 (v1)	31.3%	—

Knowledge Not comparable

GPT-5.2 Pro: —, Mistral Large 3: 35.5 (#173)

Knowledge benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
Vectara Hallucination Rate	—	14.5%
LMArena Expert	—	1421

Multimodal Not comparable

GPT-5.2 Pro: —, Mistral Large 3: 37.6 (#65)

Multimodal benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
LMArena Vision	—	1222

Multilingual Not comparable

GPT-5.2 Pro: —, Mistral Large 3: 52.6 (#79)

Multilingual benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
LMArena Non-English	—	1412
LMArena Chinese	—	1448
LMArena French	—	1456
LMArena German	—	1438
LMArena Japanese	—	1399
LMArena Korean	—	1384
LMArena Russian	—	1412
LMArena Spanish	—	1437

Instruction Following Not comparable

GPT-5.2 Pro: —, Mistral Large 3: 74.1 (#104)

Instruction Following benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
LMArena Instruction Following	—	1402

Long Context Not comparable

GPT-5.2 Pro: —, Mistral Large 3: 43.1 (#102)

Long Context benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
LMArena Longer Query	—	1413

Writing & Preference Not comparable

GPT-5.2 Pro: —, Mistral Large 3: 60.2 (#100)

Writing & Preference benchmarks
Benchmark	GPT-5.2 Pro	Mistral Large 3
LMArena Text	—	1427
LMArena Creative Writing	—	1385
EQ-Bench Creative Writing	—	1412
LMArena Multi-Turn	—	1429

Frequently asked questions

Is GPT-5.2 Pro better than Mistral Large 3?

Which is cheaper, GPT-5.2 Pro or Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 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 Large 3 share?

1 benchmark has published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Mistral Large 3 has 24.