#74
46value index
Price
$0.750blended / 1M tokens
Latency
0.58stime to first token
Speed
60 tok/soutput speed
Quality
15quality signal
ArenaArtificial Analysis
Thoughts on AI, technology, and the future we're building.
New posts every week
Thoughts on AI, technology, and the future we're building.
New posts every week
A lab-level profile for Mistral, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.
Lab rank
#19
By available Arena average
Models tracked
8
4 open-weight models
Portfolio coverage
24%
Average matched benchmark signals
Fastest model
0.58s
Mistral Large 3
Lab profile
The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.
Portfolio read
The portfolio combines 4 proprietary models and 4 open-weight models. Its average available Arena rank is 82.3, with a best category rank of #73. Average profile coverage is 24%, so model-level gaps remain visible in the cards below.
Best Arena model
Mistral Large 3
Best category rank #73
Highest coverage
Mistral Large 3
56% matched signals
Fastest response
Mistral Large 3
0.58s first token
Category leaders
Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.
Value
Quality, price, latency, and speed
Mistral Large 3
value index
Coding
Code Arena, SWE-bench, and output speed
Mistral Large 3
coding index
Agents
Search, document, code, and latency
Pixtral Large 2411
agent proxy
Reasoning
Text, document, vision, and mode signals
Mistral Medium 2508
reasoning proxy
Context
Document, search, and text proxy
Mistral Large 3
context proxy
Models from this lab with both quality and commercial price matches.
Top 2 of 2
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #74 | 46value index | $0.750blended / 1M tokens | 0.58stime to first token | 60 tok/soutput speed | 15quality signal | ArenaArtificial Analysis | |
| #83 | 38value index | $3.00blended / 1M tokens | 0.74stime to first token | 59 tok/soutput speed | 4quality signal | ArenaArtificial Analysis |
Model portfolio
Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.
Mistral Large 3
mistral-large-3
Coverage
56%
Best Arena
#73
Code
Value
#74
value index
Coding
#77
coding index
Latency
0.58s
60 tok/s
Mistral Medium 2508
mistral-medium-2508
Coverage
11%
Best Arena
#74
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Mistral Medium 2505
mistral-medium-2505
Coverage
11%
Best Arena
#76
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Devstral 2
devstral-2
Coverage
33%
Best Arena
#77
Code
Value
Not listed
No price match
Coding
#81
coding index
Latency
0.63s
34 tok/s
Devstral Medium 2507
devstral-medium-2507
Coverage
11%
Best Arena
#81
Code
Value
Not listed
No price match
Coding
#101
coding index
Latency
Not listed
Not listed
Mistral Small 2506
mistral-small-2506
Coverage
11%
Best Arena
#84
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Mistral Small 3.1 24b Instruct 2503
mistral-small-3.1-24b-instruct-2503
Coverage
11%
Best Arena
#86
Vision
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
Pixtral Large 2411
pixtral-large-2411
Coverage
44%
Best Arena
#97
Vision
Value
#83
value index
Coding
#92
coding index
Latency
0.74s
59 tok/s