Model comparison

Mistral Small 3 vs o1

o1 is the stronger model overall, scoring 40.9 to 31.2 on the Noometry Index. Mistral Small 3 costs 457× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.

Last verified October 11, 2026. 21 shared benchmarks.

Mistral Small 3

Mistral AI

31.2

Rank #278 Confirmed

o1 OpenAI

40.9

Rank #143 Confirmed

Summary

They share 21 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where o1 leads 55.6 to 32.2.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 73.3% for o1.
Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $15 / $60 for o1.
o1 accepts more context: 200K tokens versus 33K.
Mistral Small 3 has downloadable open weights; the other is API-only.

Side by side

Mistral Small 3 and o1 specifications
	Mistral Small 3	o1
Provider	Mistral AI	OpenAI
Noometry Index	31.2	40.9
Released	2025-01-30	2024-09-12
Weights	Open	Proprietary
Context window	33K	200K
Max output	16K	100K
Input $ / M tokens	$0.05	$15
Output $ / M tokens	$0.08	$60
Results tracked	24	52

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

Category by category

Coding o1 leads

Mistral Small 3: 36.5 (#207), o1: 46.1 (#70)

Coding benchmarks
Benchmark	Mistral Small 3	o1
LMArena Coding	1246	1367
Aider Polyglot	—	61.7%
WeirdML	—	47.6%
BigCodeBench Instruct	45.3%	—
LiveBench Coding	—	69.7%
BigCodeBench Complete	50.4%	—
CadEval	—	56%
HumanEval+	—	89%
MBPP+	—	80.2%

Agentic & Tool Use Not comparable

Mistral Small 3: —, o1: 24.6 (#117)

Agentic & Tool Use benchmarks
Benchmark	Mistral Small 3	o1
Cybench	—	10%
METR Time Horizons	—	51.1%

Reasoning o1 leads

Mistral Small 3: 18.9 (#273), o1: 27.9 (#111)

Reasoning benchmarks
Benchmark	Mistral Small 3	o1
Chess Puzzles	0%	15%
LMArena Hard Prompts	1233	1371
Epoch Capabilities Index	127.07	141.91
SimpleBench	—	41.7%
ARC-AGI-1	—	30.7%
EnigmaEval	—	5.7%
LiveBench Reasoning	—	91.6%
DTBench	—	74.7%
LiveBench Data Analysis	—	65.5%
LMCA	—	22.3%
LiveBench	—	75.7%

Math o1 leads

Mistral Small 3: 16.3 (#295), o1: 36.1 (#175)

Math benchmarks
Benchmark	Mistral Small 3	o1
OTIS Mock AIME 2024-2025	6.7%	73.3%
LMArena Math	1240	1388
FrontierMath (Tiers 1-3)	—	14.7%
LiveBench Math	—	80.3%
MATH Level 5	—	94.7%
FrontierMath (Feb 2025 set)	—	9.3%

Knowledge o1 leads

Mistral Small 3: 25.1 (#263), o1: 41.5 (#110)

Knowledge benchmarks
Benchmark	Mistral Small 3	o1
GPQA Diamond	47.3%	76.8%
Confabulations	25.2%	11.7%
LMArena Expert	1202	1361
Humanity's Last Exam	—	8%
SimpleQA Verified	—	41.1%

Multimodal Not comparable

Mistral Small 3: —, o1: 34.2 (#93)

Multimodal benchmarks
Benchmark	Mistral Small 3	o1
LMArena Vision	—	1168
GeoBench	—	80%
VPCT	—	37%
SpatialViz-Bench	—	41.4%

Multilingual o1 leads

Mistral Small 3: 37.3 (#236), o1: 48.6 (#142)

Multilingual benchmarks
Benchmark	Mistral Small 3	o1
LMArena Non-English	1198	1358
LMArena Chinese	1204	1394
LMArena French	1203	1344
LMArena German	1211	1337
LMArena Japanese	1111	1346
LMArena Korean	1188	1396
LMArena Russian	1216	1356
LMArena Spanish	—	1345

Instruction Following o1 leads

Mistral Small 3: 63.7 (#229), o1: 74.8 (#86)

Instruction Following benchmarks
Benchmark	Mistral Small 3	o1
LMArena Instruction Following	1214	1367
LiveBench Instruction Following	—	81.5%

Long Context o1 leads

Mistral Small 3: 37.8 (#211), o1: 50.3 (#9)

Long Context benchmarks
Benchmark	Mistral Small 3	o1
LMArena Longer Query	1246	1378
Fiction.LiveBench	—	83.3%

Writing & Preference o1 leads

Mistral Small 3: 32.2 (#280), o1: 55.6 (#144)

Writing & Preference benchmarks
Benchmark	Mistral Small 3	o1
LMArena Text	1234	1366
LMArena Creative Writing	1195	1348
LMArena Multi-Turn	1217	1369
Short-Story Creative Writing	—	70.2%
EQ-Bench Creative Writing	707	—
LiveBench Language	—	65.4%

Frequently asked questions

Is Mistral Small 3 better than o1?

Which is cheaper, Mistral Small 3 or o1?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; o1 lists at $15 and $60.

Is Mistral Small 3 or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 36.5 in the Noometry coding category.

Which has the bigger context window?

o1 does, with 200K tokens against 33K.

How many benchmarks do Mistral Small 3 and o1 share?

21 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and o1 has 52.