Compare/Devstral Medium vs Grok Build 0.1 0616

Devstral MediumvsGrok Build 0.1 0616

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Mistral

Devstral Medium

Input
$0.4/M
Output
$2/M
Speed
91 tok/s
TTFT
0.71s
SpaceXAI

Grok Build 0.1 0616

Input
$1/M
Output
$2/M
Speed
52 tok/s
TTFT
0.40s

Winner by Category

Cheaper
Devstral Medium
Faster (tok/s)
Devstral Medium
Lower Latency
Grok Build 0.1 0616
Benchmarks (7-5)
Devstral Medium

Pricing Comparison

MetricDevstral MediumGrok Build 0.1 0616
Input ($/M tokens)$0.4$1
Output ($/M tokens)$2$2
Cost for 1M input + 100K output tokens:
Devstral Medium$0.60
Grok Build 0.1 0616$1.20

Speed Comparison

Output Speed (tokens/s) — higher is better
Devstral Medium
91 tok/s
Grok Build 0.1 0616
52 tok/s
Time to First Token (seconds) — lower is better
Devstral Medium
0.71s
Grok Build 0.1 0616
0.40s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
12.439.8
Coding Index
51.5
Math Index
4.7
GPQA Diamond
49.2%89.5%
MMLU-Pro
70.8%
LiveCodeBench
33.7%
AIME 2025
4.7%
MATH-500
70.7%
Humanity's Last Exam
3.8%36.0%
SciCode
29.4%50.2%
IFBench
29.9%
TerminalBench
9.1%
Devstral Medium7 wins
5 winsGrok Build 0.1 0616

Frequently Asked Questions

Which is cheaper, Devstral Medium or Grok Build 0.1 0616?

Devstral Medium is cheaper overall. Its blended price (3:1 input/output ratio) is $0.80/M tokens vs $1.25/M for Grok Build 0.1 0616.

Which model performs better on benchmarks?

Devstral Medium wins 7 out of 12 benchmarks compared to 5 for Grok Build 0.1 0616. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Devstral Medium generates tokens faster at 91 tok/s vs 52 tok/s. However, Grok Build 0.1 0616 has lower time-to-first-token (0.40s vs 0.71s).

When should I use Devstral Medium vs Grok Build 0.1 0616?

Choose based on your priorities: Devstral Medium for lower cost, Devstral Medium for stronger benchmark performance, and Devstral Medium for faster generation. For latency-sensitive apps, check the TTFT comparison above.