Model comparison

Mistral Medium 3.5 vs Muse Spark 1.2

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 39.6 on the Noometry Index.

Last verified October 10, 2026. 15 shared benchmarks.

Mistral Medium 3.5

Mistral AI

39.6

Rank #151 Confirmed

Muse Spark 1.2

Summary

They share 15 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 16.6.
The biggest single-benchmark swing is NYT Connections (extended): 12.9% for Mistral Medium 3.5 and 79.2% for Muse Spark 1.2.
Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
Mistral Medium 3.5 has downloadable open weights; the other is API-only.

Side by side

Mistral Medium 3.5 and Muse Spark 1.2 specifications
	Mistral Medium 3.5	Muse Spark 1.2
Provider	Mistral AI	Meta
Noometry Index	39.6	49.8
Released	—	2026-08-05
Weights	Open	Proprietary
Context window	262K	1.05M
Max output	210K	131K
Input $ / M tokens	$1.50	$1.25
Output $ / M tokens	$7.50	$4.25
Results tracked	22	28

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

Category by category

Coding Muse Spark 1.2 leads

Mistral Medium 3.5: 35.7 (#208), Muse Spark 1.2: 48.6 (#49)

Coding benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
LMArena WebDev	1263	1532
LMArena Coding	1461	1497
DeepSWE	—	54.9%
FrontierSWE	—	12%
SciCode	—	56.4%
WeirdML	—	60.3%

Agentic & Tool Use Not comparable

Mistral Medium 3.5: —, Muse Spark 1.2: 29.5 (#77)

Agentic & Tool Use benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
APEX-Agents	—	36.4%
GDP.pdf	—	16%

Reasoning Muse Spark 1.2 leads

Mistral Medium 3.5: 16.6 (#290), Muse Spark 1.2: 50.4 (#32)

Reasoning benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
NYT Connections (extended)	12.9%	79.2%
LMArena Hard Prompts	1436	1490
Epoch Capabilities Index	141.42	155.18
SimpleBench	—	74.5%
Kagi LLM Benchmark	41.4%	—
CritPt	—	17.7%
DTBench	—	94.7%
LMCA	—	48.4%

Math Muse Spark 1.2 leads

Mistral Medium 3.5: 36.4 (#113), Muse Spark 1.2: 43.8 (#68)

Math benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
ProofBench	—	43%
LMArena Math	1432	—

Knowledge Muse Spark 1.2 leads

Mistral Medium 3.5: 39.3 (#123), Muse Spark 1.2: 53.9 (#49)

Knowledge benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
LMArena Expert	1431	1485
SimpleQA Verified	—	60.3%

Multimodal Muse Spark 1.2 leads

Mistral Medium 3.5: 37.6 (#64), Muse Spark 1.2: 42.6 (#24)

Multimodal benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
LMArena Vision	1222	1304

Multilingual Muse Spark 1.2 leads

Mistral Medium 3.5: 52.1 (#93), Muse Spark 1.2: 57.4 (#10)

Multilingual benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
LMArena Non-English	1405	1479
LMArena Chinese	1443	1519
LMArena Russian	1396	1494
LMArena French	1448	—
LMArena German	1453	—
LMArena Korean	1387	—
LMArena Spanish	1406	—

Instruction Following Muse Spark 1.2 leads

Mistral Medium 3.5: 74.7 (#87), Muse Spark 1.2: 77.1 (#30)

Instruction Following benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
LMArena Instruction Following	1414	1466

Long Context Muse Spark 1.2 leads

Mistral Medium 3.5: 43.2 (#101), Muse Spark 1.2: 45.4 (#35)

Long Context benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
LMArena Longer Query	1414	1483

Writing & Preference Muse Spark 1.2 leads

Mistral Medium 3.5: 58.6 (#113), Muse Spark 1.2: 72.6 (#14)

Writing & Preference benchmarks
Benchmark	Mistral Medium 3.5	Muse Spark 1.2
LMArena Text	1421	1486
LMArena Creative Writing	1372	1444
LMArena Multi-Turn	1423	1504
EQ-Bench Creative Writing	—	1840
EQ-Bench 4	993	—

Frequently asked questions

Is Mistral Medium 3.5 better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 39.6 on the Noometry Index.

Which is cheaper, Mistral Medium 3.5 or Muse Spark 1.2?

Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Mistral Medium 3.5 or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 35.7 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 262K.

How many benchmarks do Mistral Medium 3.5 and Muse Spark 1.2 share?

15 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Muse Spark 1.2 has 28.