Compare/Gemini 2.5 Pro Preview (May' 25) vs Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

Gemini 2.5 Pro Preview (May' 25)vsClaude Sonnet 5 (Adaptive Reasoning, Max Effort)

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

Google

Gemini 2.5 Pro Preview (May' 25)

Input
$1.25/M
Output
$10/M
Speed
TTFT
Anthropic

Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

Input
$2/M
Output
$10/M
Speed
76 tok/s
TTFT
184.48s

Winner by Category

Cheaper
Gemini 2.5 Pro Preview (May' 25)
Faster (tok/s)
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
Lower Latency
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
Benchmarks (0-2)
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

Pricing Comparison

MetricGemini 2.5 Pro Preview (May' 25)Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
Input ($/M tokens)$1.25$2
Output ($/M tokens)$10$10
Cost for 1M input + 100K output tokens:
Gemini 2.5 Pro Preview (May' 25)$2.25
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)$3.00

Speed Comparison

Output Speed (tokens/s) — higher is better
Gemini 2.5 Pro Preview (May' 25)
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
76 tok/s
Time to First Token (seconds) — lower is better
Gemini 2.5 Pro Preview (May' 25)
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
184.48s

Editorial Analysis

Verdict. Claude Sonnet 5 (Adaptive Reasoning, Max Effort) takes the aggregate benchmark matchup 2–0 across 2 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.

Pricing. Both models sit in the mid-tier bracket for output-token pricing. At 1.0× the per-million-token cost, Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Claude Sonnet 5 (Adaptive Reasoning, Max Effort) makes more sense when output volume is low and absolute reasoning quality justifies the premium.

Strengths. Gemini 2.5 Pro Preview (May' 25) is strongest on Intelligence Index (22.7). Claude Sonnet 5 (Adaptive Reasoning, Max Effort) leads on Coding Index (71.5), Intelligence Index (55.3).

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

Provider. Google and Anthropic sell to overlapping but distinct developer audiences: Google tends to ship frontier reasoning models with premium positioning, while Anthropic 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): Gemini 2.5 Pro Preview (May' 25) costs $187.50 ($2250/year); Claude Sonnet 5 (Adaptive Reasoning, Max Effort) costs $210.00 ($2520/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Gemini 2.5 Pro Preview (May' 25) ≈ $26.25/run, Claude Sonnet 5 (Adaptive Reasoning, Max Effort) ≈ $30.00/run. At agent/realtime scale (200M input / 100M output per million requests): Gemini 2.5 Pro Preview (May' 25) ≈ $1250/run, Claude Sonnet 5 (Adaptive Reasoning, Max Effort) ≈ $1400/run. Gemini 2.5 Pro Preview (May' 25) 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
22.755.3
Coding Index
71.5
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
Gemini 2.5 Pro Preview (May' 25)0 wins
2 winsClaude Sonnet 5 (Adaptive Reasoning, Max Effort)

Frequently Asked Questions

Which is cheaper, Gemini 2.5 Pro Preview (May' 25) or Claude Sonnet 5 (Adaptive Reasoning, Max Effort)?

Gemini 2.5 Pro Preview (May' 25) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.44/M tokens vs $4.00/M for Claude Sonnet 5 (Adaptive Reasoning, Max Effort).

Which model performs better on benchmarks?

Claude Sonnet 5 (Adaptive Reasoning, Max Effort) wins 2 out of 12 benchmarks compared to 0 for Gemini 2.5 Pro Preview (May' 25). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Claude Sonnet 5 (Adaptive Reasoning, Max Effort) generates tokens faster at 76 tok/s vs — tok/s. However, Claude Sonnet 5 (Adaptive Reasoning, Max Effort) has lower time-to-first-token (184.48s vs —s).

When should I use Gemini 2.5 Pro Preview (May' 25) vs Claude Sonnet 5 (Adaptive Reasoning, Max Effort)?

Choose based on your priorities: Gemini 2.5 Pro Preview (May' 25) for lower cost, Claude Sonnet 5 (Adaptive Reasoning, Max Effort) for stronger benchmark performance, and Claude Sonnet 5 (Adaptive Reasoning, Max Effort) for faster generation. For latency-sensitive apps, check the TTFT comparison above.