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
$0.04/M
Output
$0.17/M
Speed
TTFT
Mistral

Ministral 3 8B

Input
$0.15/M
Output
$0.15/M
Speed
120 tok/s
TTFT
0.76s

Winner by Category

Cheaper
Sarvam 105B (high)
Faster (tok/s)
Ministral 3 8B
Lower Latency
Ministral 3 8B
Benchmarks (1-1)
Tie

Pricing Comparison

MetricSarvam 105B (high)Ministral 3 8B
Input ($/M tokens)$0.04$0.15
Output ($/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)
Ministral 3 8B
120 tok/s
Time to First Token (seconds) — lower is better
Sarvam 105B (high)
Ministral 3 8B
0.76s

Editorial Analysis

Verdict. Sarvam 105B (high) and Ministral 3 8B split the benchmark comparison evenly at 1–1. The tiebreaker here is price, speed, and what you actually run them on.

Pricing. Both models sit in the budget bracket for output-token pricing. At 1.1× the per-million-token cost, Ministral 3 8B is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Ministral 3 8B makes more sense when output volume is low and absolute reasoning quality justifies the premium.

Strengths. Sarvam 105B (high) is strongest on Intelligence Index (11.9). Ministral 3 8B leads on Coding Index (9.7), Intelligence Index (9.0).

Speed. Speed data is incomplete for this pair; benchmark and price should decide.

Provider. Sarvam and Mistral sell to overlapping but distinct developer audiences: Sarvam tends to ship frontier reasoning models with premium positioning, while Mistral often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.

Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Sarvam 105B (high) costs $3.75 ($45/year); Ministral 3 8B costs $6.75 ($81/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Sarvam 105B (high) ≈ $0.54/run, Ministral 3 8B ≈ $1.05/run. At agent/realtime scale (200M input / 100M output per million requests): Sarvam 105B (high) ≈ $25/run, Ministral 3 8B ≈ $45/run. Sarvam 105B (high) becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.

Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.

Head-to-head deltas

  • Benchmark wins tie exactly at 1–1. The tiebreaker on raw benchmark parity will be price, speed, or capability coverage.

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
11.99.0
Coding Index
9.7
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
Sarvam 105B (high)1 wins
1 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?

It's a tie — both models win 1 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Ministral 3 8B generates tokens faster at 120 tok/s vs — tok/s. However, Ministral 3 8B has lower time-to-first-token (0.76s vs —s).

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

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