Compare/Apertus 70B Instruct vs Gemini 3 Flash Preview (Reasoning)

Apertus 70B InstructvsGemini 3 Flash Preview (Reasoning)

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

Swiss AI Initiative

Apertus 70B Instruct

Input
$0.82/M
Output
$2.92/M
Speed
TTFT
Google

Gemini 3 Flash Preview (Reasoning)

Input
$0.5/M
Output
$3/M
Speed
189 tok/s
TTFT
6.57s

Winner by Category

Cheaper
Gemini 3 Flash Preview (Reasoning)
Faster (tok/s)
Gemini 3 Flash Preview (Reasoning)
Lower Latency
Gemini 3 Flash Preview (Reasoning)
Benchmarks (0-1)
Gemini 3 Flash Preview (Reasoning)

Pricing Comparison

MetricApertus 70B InstructGemini 3 Flash Preview (Reasoning)
Input ($/M tokens)$0.82$0.5
Output ($/M tokens)$2.92$3
Cost for 1M input + 100K output tokens:
Apertus 70B Instruct$1.11
Gemini 3 Flash Preview (Reasoning)$0.80

Speed Comparison

Output Speed (tokens/s) — higher is better
Apertus 70B Instruct
Gemini 3 Flash Preview (Reasoning)
189 tok/s
Time to First Token (seconds) — lower is better
Apertus 70B Instruct
Gemini 3 Flash Preview (Reasoning)
6.57s

Editorial Analysis

Verdict. Gemini 3 Flash Preview (Reasoning) takes the aggregate benchmark matchup 1–0 across 1 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.

Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, Apertus 70B Instruct is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Apertus 70B Instruct makes more sense when output volume is low and absolute reasoning quality justifies the premium.

Strengths. Apertus 70B Instruct is strongest on Intelligence Index (2.0). Gemini 3 Flash Preview (Reasoning) leads on Intelligence Index (38.7).

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

Provider. Swiss AI Initiative and Google sell to overlapping but distinct developer audiences: Swiss AI Initiative tends to ship frontier reasoning models with premium positioning, while Google 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): Apertus 70B Instruct costs $68.40 ($821/year); Gemini 3 Flash Preview (Reasoning) costs $60.00 ($720/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Apertus 70B Instruct ≈ $9.94/run, Gemini 3 Flash Preview (Reasoning) ≈ $8.50/run. At agent/realtime scale (200M input / 100M output per million requests): Apertus 70B Instruct ≈ $456/run, Gemini 3 Flash Preview (Reasoning) ≈ $400/run. Gemini 3 Flash Preview (Reasoning) 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.

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
2.038.7
Coding Index
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
Apertus 70B Instruct0 wins
1 winsGemini 3 Flash Preview (Reasoning)

Frequently Asked Questions

Which is cheaper, Apertus 70B Instruct or Gemini 3 Flash Preview (Reasoning)?

Gemini 3 Flash Preview (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.13/M tokens vs $1.34/M for Apertus 70B Instruct.

Which model performs better on benchmarks?

Gemini 3 Flash Preview (Reasoning) wins 1 out of 12 benchmarks compared to 0 for Apertus 70B Instruct. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Gemini 3 Flash Preview (Reasoning) generates tokens faster at 189 tok/s vs — tok/s. However, Gemini 3 Flash Preview (Reasoning) has lower time-to-first-token (6.57s vs —s).

When should I use Apertus 70B Instruct vs Gemini 3 Flash Preview (Reasoning)?

Choose based on your priorities: Gemini 3 Flash Preview (Reasoning) for lower cost, Gemini 3 Flash Preview (Reasoning) for stronger benchmark performance, and Gemini 3 Flash Preview (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.