Devstral Medium
Zero-eval
by Mistral AI
About
Devstral Medium is a language model developed by Mistral AI. It achieves strong performance with an average score of 61.6% across 1 benchmarks. Notable strengths include SWE-Bench Verified (61.6%). It supports a 256K token context window for handling large documents. The model is available through 1 API provider. Released in 2025, it represents Mistral AI's latest advancement in AI technology.
Pricing Range
Input (per 1M)$0.40 -$0.40
Output (per 1M)$2.00 -$2.00
Providers1
Timeline
AnnouncedJul 10, 2025
ReleasedJul 10, 2025
Specifications
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
1 benchmarks
Average Score
61.6%
Best Score
61.6%
High Performers (80%+)
0Performance Metrics
Max Context Window
256.0KAvg Throughput
137.1 tok/sAvg Latency
0msTop Categories
general
61.6%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
SWE-Bench Verified
Rank #9 of 28
#6Gemini 2.5 Pro
63.2%
#7Gemini 2.5 Pro Preview 06-05
67.2%
#8o4-mini
68.1%
#9Devstral Medium
61.6%
#10Gemini 2.5 Flash
60.4%
#11DeepSeek-R1-0528
57.6%
#12GPT-4.1
54.6%
All Benchmark Results for Devstral Medium
Complete list of benchmark scores with detailed information
SWE-Bench Verified SWE-Bench Verified benchmark | general | text | 0.62 | 61.6% | Self-reported |
Resources