Compare/Devstral Small (May '25) vs Llama 3.1 Instruct 8B

Devstral Small (May '25)vsLlama 3.1 Instruct 8B

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

Mistral

Devstral Small (May '25)

Input
$0.06/M
Output
$0.12/M
Speed
TTFT
Meta

Llama 3.1 Instruct 8B

Input
$0.1/M
Output
$0.1/M
Speed
194 tok/s
TTFT
0.47s

Winner by Category

Cheaper
Devstral Small (May '25)
Faster (tok/s)
Llama 3.1 Instruct 8B
Lower Latency
Devstral Small (May '25)
Benchmarks (9-3)
Devstral Small (May '25)

Pricing Comparison

MetricDevstral Small (May '25)Llama 3.1 Instruct 8B
Input ($/M tokens)$0.06$0.1
Output ($/M tokens)$0.12$0.1
Cost for 1M input + 100K output tokens:
Devstral Small (May '25)$0.07
Llama 3.1 Instruct 8B$0.11

Speed Comparison

Output Speed (tokens/s) — higher is better
Devstral Small (May '25)
Llama 3.1 Instruct 8B
194 tok/s
Time to First Token (seconds) — lower is better
Devstral Small (May '25)
Llama 3.1 Instruct 8B
0.47s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
18.011.8
Coding Index
12.24.9
Math Index
4.3
GPQA Diamond
43.4%25.9%
MMLU-Pro
63.2%47.6%
LiveCodeBench
25.8%11.6%
AIME 2025
4.3%
MATH-500
68.4%51.9%
Humanity's Last Exam
4.0%5.1%
SciCode
24.5%13.2%
IFBench
31.6%28.6%
TerminalBench
6.1%0.8%
Devstral Small (May '25)9 wins
3 winsLlama 3.1 Instruct 8B

Frequently Asked Questions

Which is cheaper, Devstral Small (May '25) or Llama 3.1 Instruct 8B?

Devstral Small (May '25) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.07/M tokens vs $0.10/M for Llama 3.1 Instruct 8B.

Which model performs better on benchmarks?

Devstral Small (May '25) wins 9 out of 12 benchmarks compared to 3 for Llama 3.1 Instruct 8B. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Llama 3.1 Instruct 8B generates tokens faster at 194 tok/s vs 0 tok/s. Devstral Small (May '25) also has lower time-to-first-token (0.00s vs 0.47s).

When should I use Devstral Small (May '25) vs Llama 3.1 Instruct 8B?

Choose based on your priorities: Devstral Small (May '25) for lower cost, Devstral Small (May '25) for stronger benchmark performance, and Llama 3.1 Instruct 8B for faster generation. For latency-sensitive apps, check the TTFT comparison above.