← All Comparisons
Claude Haiku 4.5 vs Gemini 3 Flash
A detailed comparison of Claude Haiku 4.5 (Anthropic) and Gemini 3 Flash (Google) across pricing, performance, and features.
Pricing Comparison
| Metric | Claude Haiku 4.5 | Gemini 3 Flash | Difference |
|---|---|---|---|
| Input / 1M tokens | $0.80 | $0.50 | -38% |
| Output / 1M tokens | $4.00 | $3.00 | -25% |
| Context window | 200K | 1M | — |
| Max output | 8.192K | 65.536K | — |
Benchmark Comparison
| Benchmark | Claude Haiku 4.5 | Gemini 3 Flash |
|---|---|---|
| MMLU-Pro | 69.4% | 78% |
| HumanEval | 88.1% | 90% |
Capabilities
| Capability | Claude Haiku 4.5 | Gemini 3 Flash |
|---|---|---|
| code | ✓ | ✓ |
| reasoning | ✗ | ✓ |
| text | ✓ | ✓ |
| tool-use | ✓ | ✓ |
| vision | ✓ | ✓ |
Claude Haiku 4.5 Strengths
- ✓Very fast responses
- ✓Cheapest Anthropic option
- ✓Good for classification and extraction
Claude Haiku 4.5 Weaknesses
- ✗Weakest reasoning in the Claude family
- ✗Can struggle with nuanced instructions
Gemini 3 Flash Strengths
- ✓1M context at budget pricing
- ✓Very fast
- ✓Free tier available via Google AI Studio
Gemini 3 Flash Weaknesses
- ✗Less capable than Pro on complex reasoning
- ✗Audio input priced separately ($1/1M)
Quick Verdict
Best value: Gemini 3 Flash is the more affordable option at $0.5/$3 per 1M tokens.
Higher benchmarks: Gemini 3 Flash scores higher on average across available benchmarks (84.0% avg).
Larger context: Gemini 3 Flash supports 1M tokens.
Choose Gemini 3 Flash if cost matters most. Choose Claude Haiku 4.5 if you need the best possible quality for complex tasks.