Claude 4.5 Haiku (Non-reasoning) vs Gemini 3 Pro Preview (high)
Comparing 2 AI models · 5 benchmarks · Anthropic, Google
Most Affordable
An
Claude 4.5 Haiku (Non-reasoning)
$1.00/1M
Highest Intelligence
Go
Gemini 3 Pro Preview (high)
90.8% GPQA
Best for Coding
Go
Gemini 3 Pro Preview (high)
62.3 Coding Index
Price Difference
2.0x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
5 tests
An
Claude 4.5 Haiku (Non-reasoning)
0
No clear wins
Go
Gemini 3 Pro Preview (high)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | An Claude 4.5 Haiku (Non-reasoning) | Go Gemini 3 Pro Preview (high) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $1.00/1M | $2.00/1M |
| Output Cost | $5.00/1M | $12.00/1M |
| Blended Cost 3:1 input/output ratio | $2.00/1M | $4.50/1M |
| Specifications | ||
| Organization Model creator | Anthropic | |
| Release Date Launch date | Oct 15, 2025 | Nov 18, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 99.9 tok/s | 138.9 tok/s |
| Time to First Token (TTFT) Initial response delay | 1012ms | 26684ms |
| Latency Time to first answer token | 1012ms | |