Compare/Mistral Small 4 (Reasoning) vs gpt-oss-120B (low)

Mistral Small 4 (Reasoning)vsgpt-oss-120B (low)

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

Mistral

Mistral Small 4 (Reasoning)

Input
$0.15/M
Output
$0.6/M
Speed
TTFT
OpenAI

gpt-oss-120B (low)

Input
$0.15/M
Output
$0.6/M
Speed
255 tok/s
TTFT
0.51s

Winner by Category

Cheaper
Tie
Faster (tok/s)
gpt-oss-120B (low)
Lower Latency
Mistral Small 4 (Reasoning)
Benchmarks (6-5)
Mistral Small 4 (Reasoning)

Pricing Comparison

MetricMistral Small 4 (Reasoning)gpt-oss-120B (low)
Input ($/M tokens)$0.15$0.15
Output ($/M tokens)$0.6$0.6
Cost for 1M input + 100K output tokens:
Mistral Small 4 (Reasoning)$0.21
gpt-oss-120B (low)$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
Mistral Small 4 (Reasoning)
gpt-oss-120B (low)
255 tok/s
Time to First Token (seconds) — lower is better
Mistral Small 4 (Reasoning)
gpt-oss-120B (low)
0.51s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
26.924.5
Coding Index
24.315.5
Math Index
66.7
GPQA Diamond
76.9%67.2%
MMLU-Pro
77.5%
LiveCodeBench
70.7%
AIME 2025
66.7%
MATH-500
Humanity's Last Exam
9.5%5.2%
SciCode
38.0%36.0%
IFBench
48.2%58.3%
TerminalBench
17.4%5.3%
Mistral Small 4 (Reasoning)6 wins
5 winsgpt-oss-120B (low)

Frequently Asked Questions

Which is cheaper, Mistral Small 4 (Reasoning) or gpt-oss-120B (low)?

Both models have similar pricing. Check the detailed breakdown above for input vs output token costs.

Which model performs better on benchmarks?

Mistral Small 4 (Reasoning) wins 6 out of 12 benchmarks compared to 5 for gpt-oss-120B (low). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-120B (low) generates tokens faster at 255 tok/s vs 0 tok/s. Mistral Small 4 (Reasoning) also has lower time-to-first-token (0.00s vs 0.51s).

When should I use Mistral Small 4 (Reasoning) vs gpt-oss-120B (low)?

Choose based on your priorities: both are similarly priced, Mistral Small 4 (Reasoning) for stronger benchmark performance, and gpt-oss-120B (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.