Compare/Sarvam 105B (high) vs Ministral 3 8B

Sarvam 105B (high)vsMinistral 3 8B

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

Sarvam

Sarvam 105B (high)

Input
$0.042/M
Output
$0.17/M
Speed
155 tok/s
TTFT
1.20s
Mistral

Ministral 3 8B

Input
$0.15/M
Output
$0.15/M
Speed
100 tok/s
TTFT
0.43s

Winner by Category

Cheaper
Sarvam 105B (high)
Faster (tok/s)
Sarvam 105B (high)
Lower Latency
Ministral 3 8B
Benchmarks (5-6)
Ministral 3 8B

Pricing Comparison

MetricSarvam 105B (high)Ministral 3 8B
Input ($/M tokens)$0.042$0.15
Output ($/M tokens)$0.17$0.15
Cost for 1M input + 100K output tokens:
Sarvam 105B (high)$0.06
Ministral 3 8B$0.16

Speed Comparison

Output Speed (tokens/s) — higher is better
Sarvam 105B (high)
155 tok/s
Ministral 3 8B
100 tok/s
Time to First Token (seconds) — lower is better
Sarvam 105B (high)
1.20s
Ministral 3 8B
0.43s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
11.99.0
Coding Index
9.7
Math Index
31.7
GPQA Diamond
73.8%47.1%
MMLU-Pro
64.2%
LiveCodeBench
30.3%
AIME 2025
31.7%
MATH-500
Humanity's Last Exam
10.1%4.3%
SciCode
26.4%20.8%
IFBench
34.4%29.1%
TerminalBench
1.5%4.5%
Sarvam 105B (high)5 wins
6 winsMinistral 3 8B

Frequently Asked Questions

Which is cheaper, Sarvam 105B (high) or Ministral 3 8B?

Sarvam 105B (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.07/M tokens vs $0.15/M for Ministral 3 8B.

Which model performs better on benchmarks?

Ministral 3 8B wins 6 out of 12 benchmarks compared to 5 for Sarvam 105B (high). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Sarvam 105B (high) generates tokens faster at 155 tok/s vs 100 tok/s. However, Ministral 3 8B has lower time-to-first-token (0.43s vs 1.20s).

When should I use Sarvam 105B (high) vs Ministral 3 8B?

Choose based on your priorities: Sarvam 105B (high) for lower cost, Ministral 3 8B for stronger benchmark performance, and Sarvam 105B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.