Model Comparison
Google's Gemini 2.0 Flash beats Anthropic's Claude 3.5 Sonnet on both price and benchmarks — here's the full breakdown.
Data last updated March 4, 2026
Gemini 2.0 Flash is the clear winner — cheaper and higher-scoring than Claude 3.5 Sonnet. Claude 3.5 Sonnet costs $0.03 per request vs $0.0009 for Gemini 2.0 Flash (at 5K input / 1K output tokens). Claude 3.5 Sonnet's only edge might be vendor-specific features or API ecosystem.
| Metric | Claude 3.5 Sonnet | Gemini 2.0 Flash |
|---|---|---|
| Intelligence IndexComposite score from MMLU-Pro, GPQA, and AIME. Higher is better. | 15.9 | 18.5 |
| MMLU-ProGeneral knowledge and reasoning. Higher is better. | 0.8 | 0.8 |
| GPQAGraduate-level science questions. Higher is better. | 0.6 | 0.6 |
| AIMEMathematical problem solving. Higher is better. | 0.2 | 0.3 |
| Context windowMax tokens per request. Larger handles more text. | 200,000 | 1,000,000 |
List prices as published by the provider. Not adjusted for token efficiency.
| Metric | Claude 3.5 Sonnet | Gemini 2.0 Flash |
|---|---|---|
| Input price / 1M tokens | $3.00 | $0.10 |
| Output price / 1M tokens | $15.00 | $0.40 |
| Cache hit price / 1M tokens | $0.30 | $0.02 |
Cost per IQ point based on a typical request of 5,000 input and 1,000 output tokens.
Cheaper (list price)
Gemini 2.0 Flash
Higher Benchmarks
Gemini 2.0 Flash
Better Value ($/IQ point)
Gemini 2.0 Flash
Claude 3.5 Sonnet
$0.0019 / IQ point
Gemini 2.0 Flash
$0.000049 / IQ point
Gemini 2.0 Flash is dramatically cheaper — 33x less per request than Claude 3.5 Sonnet. Gemini 2.0 Flash is cheaper on both input ($0.1/M vs $3.0/M) and output ($0.4/M vs $15.0/M). At a fraction of the cost, Gemini 2.0 Flash saves significantly in production workloads. This comparison assumes a typical request of 5,000 input and 1,000 output tokens (5:1 ratio). Actual ratios vary by workload — chat and completion tasks typically run 2:1, code review around 3:1, document analysis and summarization 10:1 to 50:1, and embedding workloads are pure input with no output tokens.
Gemini 2.0 Flash scores higher overall (18.5 vs 15.9). Gemini 2.0 Flash leads on AIME (0.33 vs 0.16), with both within 5% on MMLU-Pro and GPQA. If mathematical reasoning matters, Gemini 2.0 Flash's AIME score of 0.33 gives it an edge.
Gemini 2.0 Flash has a much larger context window — 1,000,000 tokens vs Claude 3.5 Sonnet at 200,000 tokens. That's roughly 1,333 vs 266 pages of text. Gemini 2.0 Flash's window can handle entire codebases or book-length documents; Claude 3.5 Sonnet works better for shorter inputs.
Gemini 2.0 Flash offers dramatically better value — $0.000049 per intelligence point vs Claude 3.5 Sonnet at $0.0019. Gemini 2.0 Flash is both cheaper and higher-scoring, making it the clear value pick. You don't sacrifice quality to save money with Gemini 2.0 Flash.
With prompt caching, Gemini 2.0 Flash is dramatically cheaper — 31x less per request than Claude 3.5 Sonnet. Caching saves 45% on Claude 3.5 Sonnet and 42% on Gemini 2.0 Flash compared to standard input prices. Both models benefit from caching at similar rates, so the uncached price comparison holds.
Pricing verified against official vendor documentation. Updated daily. See our methodology.
Create an account, install the SDK, and see your first margin data in minutes.
See My Margin DataNo credit card required