Compare/Devstral Small 2 vs o3

Devstral Small 2vso3

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

Mistral

Devstral Small 2

Input
$0/M
Output
$0/M
Speed
67 tok/s
TTFT
0.61s
OpenAI

o3

Input
$2/M
Output
$8/M
Speed
125 tok/s
TTFT
6.65s

Winner by Category

Cheaper
Devstral Small 2
Faster (tok/s)
o3
Lower Latency
Devstral Small 2
Benchmarks (1-11)
o3

Pricing Comparison

MetricDevstral Small 2o3
Input ($/M tokens)$0$2
Output ($/M tokens)$0$8
Cost for 1M input + 100K output tokens:
Devstral Small 2$0.00
o3$2.80

Speed Comparison

Output Speed (tokens/s) — higher is better
Devstral Small 2
67 tok/s
o3
125 tok/s
Time to First Token (seconds) — lower is better
Devstral Small 2
0.61s
o3
6.65s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
17.430.4
Coding Index
29.3
Math Index
34.388.3
GPQA Diamond
53.2%82.7%
MMLU-Pro
67.8%85.3%
LiveCodeBench
34.8%80.8%
AIME 2025
34.3%88.3%
MATH-500
99.2%
Humanity's Last Exam
3.4%20.0%
SciCode
28.8%41.0%
IFBench
31.2%71.4%
TerminalBench
16.7%37.1%
Devstral Small 21 wins
11 winso3

Frequently Asked Questions

Which is cheaper, Devstral Small 2 or o3?

Devstral Small 2 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $3.50/M for o3.

Which model performs better on benchmarks?

o3 wins 11 out of 12 benchmarks compared to 1 for Devstral Small 2. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

o3 generates tokens faster at 125 tok/s vs 67 tok/s. Devstral Small 2 also has lower time-to-first-token (0.61s vs 6.65s).

When should I use Devstral Small 2 vs o3?

Choose based on your priorities: Devstral Small 2 for lower cost, o3 for stronger benchmark performance, and o3 for faster generation. For latency-sensitive apps, check the TTFT comparison above.