Benchmark suiteUpdated May 27, 2026

Devstral 2.

A model-level benchmark profile for Devstral 2, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

Mistral lab page

Lab

Mistral

Open weights

Coverage

33%

3 of 9 tracked signals

Best Arena rank

#77

WebDev Arena

Best suite

#81

Coding / 19

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

Devstral 2 is strongest on coding.

33% coverage

Its best composite result is rank #81 in the coding view, with a 19 coding index. The strongest raw Arena signal is WebDev Arena at rank #77 with 1,583 public votes.

Best current lane

Coding

#81 / 19 coding index

Strongest raw signal

Code

#77, 1199 score

Commercial posture

Not listed

0.63s first token / 34 tok/s

Coverage gaps

Text ArenaVision ArenaSearch ArenaDocument ArenaBlended priceSWE-bench

Profile completeness

3 of 9 signals matched

33%

Arena categories

1/5

Code

Commercial match

Live

Devstral 2

SWE-bench

Not listed

No confident software benchmark row

Raw identifier

devstral-2

Open weights

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

WebDev Arena

Arena category

1,199#77

1182-1216 CI

1,583 votes

May 25, 2026

Arena public leaderboard dataset

Vision Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

Not listed

No confident SWE-bench row matched to this model.

Coverage gap

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

Not listed

USD / 1M tokens

Input price

Not listed

USD / 1M input tokens

Output price

Not listed

USD / 1M output tokens

Latency

0.63s

Median time to first token

Output speed

34 tok/s

Median generation speed

Matched source row

Devstral 2

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

Not listed

Not enough matched source rows for this composite view.

Coding

Code Arena, SWE-bench, and output speed

#8119

coding index

Code Arena rank #771,199

No confident matchNot listed

output speed34 tok/s

Agents