Model comparison

GPT-4 Turbo vs Mistral Large 3

Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.3 on the Noometry Index.

Last verified October 10, 2026. 18 shared benchmarks.

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Mistral Large 3

Mistral AI

38.6

Rank #172 Confirmed

Summary

They share 18 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and Mistral Large 3 in 8 categories; 7 gaps are clear of the uncertainty.
The widest gap is in math, where Mistral Large 3 leads 36.0 to 8.6.
Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
Mistral Large 3 accepts more context: 262K tokens versus 128K.
Mistral Large 3 has downloadable open weights; the other is API-only.

Side by side

GPT-4 Turbo and Mistral Large 3 specifications
	GPT-4 Turbo	Mistral Large 3
Provider	OpenAI	Mistral AI
Noometry Index	30.3	38.6
Released	2023-11-06	2025-12-02
Weights	Proprietary	Open
Context window	128K	262K
Max output	4K	8K
Input $ / M tokens	$10	$0.25
Output $ / M tokens	$30	$0.75
Results tracked	36	24

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

Category by category

Coding Too close to call

GPT-4 Turbo: 33.4 (#247), Mistral Large 3: 34.1 (#230)

Coding benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Coding	1268	1447
LMArena WebDev	—	1230
WeirdML	18%	—
BigCodeBench Instruct	48.2%	—
BigCodeBench Complete	58.2%	—
HumanEval+	86.6%	—
MBPP+	73.3%	—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Mistral Large 3: —

Agentic & Tool Use benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
METR Time Horizons	36.7%	—

Reasoning Too close to call

GPT-4 Turbo: 14.9 (#311), Mistral Large 3: 14.6 (#314)

Reasoning benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Hard Prompts	1251	1429
SimpleBench	25.1%	—
Kagi LLM Benchmark	—	50.9%
NYT Connections (extended)	—	7.5%
Chess Puzzles	6%	—
Thematic Generalization	—	23%
DTBench	61.6%	—
LMCA	9.8%	—
Epoch Capabilities Index	127.25	—
ForecastBench	59.4	—

Math Mistral Large 3 leads

GPT-4 Turbo: 8.6 (#316), Mistral Large 3: 36.0 (#131)

Math benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Math	1272	1415
FrontierMath (Tiers 1-3)	0.7%	—
OTIS Mock AIME 2024-2025	6.7%	—
MATH Level 5	46.7%	—

Knowledge Mistral Large 3 leads

GPT-4 Turbo: 24.3 (#263), Mistral Large 3: 35.5 (#173)

Knowledge benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Expert	1223	1421
GPQA Diamond	46.6%	—
Confabulations	28.4%	—
Vectara Hallucination Rate	—	14.5%
MMLU	81.3%	—

Multimodal Mistral Large 3 leads

GPT-4 Turbo: 30.0 (#104), Mistral Large 3: 37.6 (#65)

Multimodal benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Vision	1090	1222

Multilingual Mistral Large 3 leads

GPT-4 Turbo: 40.7 (#211), Mistral Large 3: 52.6 (#79)

Multilingual benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Non-English	1245	1412
LMArena Chinese	1242	1448
LMArena French	1275	1456
LMArena German	1259	1438
LMArena Japanese	1194	1399
LMArena Korean	1187	1384
LMArena Russian	1259	1412
LMArena Spanish	1260	1437

Instruction Following Mistral Large 3 leads

GPT-4 Turbo: 66.0 (#211), Mistral Large 3: 74.1 (#104)

Instruction Following benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Instruction Following	1250	1402

Long Context Mistral Large 3 leads

GPT-4 Turbo: 38.0 (#200), Mistral Large 3: 43.1 (#102)

Long Context benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Longer Query	1254	1413

Writing & Preference Mistral Large 3 leads

GPT-4 Turbo: 47.9 (#201), Mistral Large 3: 60.2 (#100)

Writing & Preference benchmarks
Benchmark	GPT-4 Turbo	Mistral Large 3
LMArena Text	1272	1427
LMArena Creative Writing	1269	1385
LMArena Multi-Turn	1267	1429
EQ-Bench Creative Writing	—	1412

Frequently asked questions

Is GPT-4 Turbo better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.3 on the Noometry Index.

Which is cheaper, GPT-4 Turbo 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-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Mistral Large 3 better for coding?

They score almost the same on coding (33.4 vs 34.1); test both on your own repository before choosing.

Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 128K.

How many benchmarks do GPT-4 Turbo and Mistral Large 3 share?

18 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Mistral Large 3 has 24.