Model comparison

Mistral vs o3

o3 is the stronger model overall, scoring 47.4 to 29.4 on the Noometry Index.

Last verified October 10, 2026. 22 shared benchmarks.

Mistral

Mistral AI

29.4

Rank #297 Confirmed

o3 OpenAI

47.4

Rank #53 Confirmed

Summary

They share 22 benchmarks with published results for both. Mistral scores higher in 0 categories and o3 in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where o3 leads 54.5 to 16.3.
The biggest single-benchmark swing is Omni-MATH: 7.2% for Mistral and 71.4% for o3.

Side by side

Mistral and o3 specifications
	Mistral	o3
Provider	Mistral AI	OpenAI
Noometry Index	29.4	47.4
Released	—	2025-04-16
Weights	Proprietary	Proprietary
Context window	—	200K
Max output	—	100K
Input $ / M tokens	—	$2
Output $ / M tokens	—	$8
Results tracked	22	63

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

Category by category

Coding o3 leads

Mistral: 33.2 (#249), o3: 47.3 (#57)

Coding benchmarks
Benchmark	Mistral	o3
LMArena Coding	1162	1408
SWE-bench Verified	—	62.3%
SWE-bench Verified (bash only)	—	58.4%
Aider Polyglot	—	81.3%
GSO	—	8.8%
WeirdML	—	52.4%
CadEval	—	74%
ALE-Bench	—	933.55

Agentic & Tool Use Not comparable

Mistral: —, o3: 34.3 (#42)

Agentic & Tool Use benchmarks
Benchmark	Mistral	o3
Berkeley Function Calling Leaderboard	—	63%
GDPval	—	30.8%
DeepResearch Bench	—	45.2%
OSWorld	—	23%
LMArena Search	—	1144
METR Time Horizons	—	65.4%

Reasoning o3 leads

Mistral: 21.3 (#199), o3: 32.1 (#66)

Reasoning benchmarks
Benchmark	Mistral	o3
LMArena Hard Prompts	1149	1402
ARC-AGI-2	—	6.5%
SimpleBench	—	53.1%
Kagi LLM Benchmark	—	67.6%
ARC-AGI-1	—	60.8%
CritPt	—	1.4%
Chess Puzzles	—	38%
EnigmaEval	—	13.1%
Mystery Game Puzzles	—	29%
DTBench	—	84.8%
LMCA	—	39.7%
Epoch Capabilities Index	—	146.88
ForecastBench	—	62.5

Math o3 leads

Mistral: 20.5 (#275), o3: 48.9 (#49)

Math benchmarks
Benchmark	Mistral	o3
Omni-MATH	7.2%	71.4%
LMArena Math	1180	1426
FrontierMath (Tiers 1-3)	—	33.3%
OTIS Mock AIME 2024-2025	—	84.4%
MATH Level 5	—	97.8%
FrontierMath (Feb 2025 set)	—	18.7%
FrontierMath Tier 4 (v1)	—	2.1%

Knowledge o3 leads

Mistral: 16.3 (#283), o3: 54.5 (#47)

Knowledge benchmarks
Benchmark	Mistral	o3
MMLU-Pro	27.7%	85.9%
GPQA (HELM)	30.3%	75.3%
LMArena Expert	1125	1403
GPQA Diamond	—	81.8%
Humanity's Last Exam	—	20.3%
SimpleQA Verified	—	49.4%
Confabulations	—	14.4%

Multimodal Not comparable

Mistral: —, o3: 40.7 (#35)

Multimodal benchmarks
Benchmark	Mistral	o3
LMArena Vision	—	1214
GeoBench	—	74%
VPCT	—	52%

Multilingual o3 leads

Mistral: 33.0 (#249), o3: 51.9 (#99)

Multilingual benchmarks
Benchmark	Mistral	o3
LMArena Non-English	1129	1402
LMArena Chinese	1109	1438
LMArena French	1179	1430
LMArena German	1155	1420
LMArena Japanese	1012	1404
LMArena Korean	1032	1371
LMArena Russian	1168	1407
LMArena Spanish	1143	1395

Instruction Following o3 leads

Mistral: 52.9 (#283), o3: 73.0 (#122)

Instruction Following benchmarks
Benchmark	Mistral	o3
IFEval	56.8%	86.9%
LMArena Instruction Following	1152	1368

Long Context o3 leads

Mistral: 35.0 (#240), o3: 53.2 (#6)

Long Context benchmarks
Benchmark	Mistral	o3
LMArena Longer Query	1154	1372
Fiction.LiveBench	—	88.9%
CL-bench	—	17.8%

Writing & Preference o3 leads

Mistral: 37.2 (#255), o3: 63.7 (#62)

Writing & Preference benchmarks
Benchmark	Mistral	o3
LMArena Text	1165	1410
LMArena Creative Writing	1158	1359
WildBench	66%	86.1%
LMArena Multi-Turn	1147	1405
Short-Story Creative Writing	—	83.9%
EQ-Bench Creative Writing	—	1676

Frequently asked questions

Is Mistral better than o3?