Claude Sonnet 5vsGemini 3.5 Flash
Across 8 shared benchmarks, Claude Sonnet 5 leads overall: Claude Sonnet 5 wins 6, Gemini 3.5 Flash wins 2, with 0 ties and an average score difference of +3.17.
Claude Sonnet 5
Anthropic · 2026-06-30 · Multimodal model
Gemini 3.5 Flash
Google Deep Mind · 2026-06-20 · Multimodal model
Claude Sonnet 56 wins(75%)(25%)2 winsGemini 3.5 Flash
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
AI Agent - Tool Usage
Claude Sonnet 5 2/2| Benchmark | Claude Sonnet 5 | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 80.4018 / 44极高强度思考（工具） | 76.2023 / 44Thinking High (With Tools) | +4.20 |
| OSWorld-Verified | 81.206 / 26极高强度思考（工具） | 78.4010 / 26Thinking High (With Tools) | +2.80 |
Math and Reasoning
Claude Sonnet 5 2/2| Benchmark | Claude Sonnet 5 | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| FrontierMath v2 | 65.6117 / 34最高（无工具） | 62.8118 / 34Thinking High (No Tools) | +2.81 |
| FrontierMath Tier 4 v2 | 29.2716 / 34最高（无工具） | 26.8318 / 34Thinking High (No Tools) | +2.44 |
Coding and Software Engineer
Claude Sonnet 5 1/1| Benchmark | Claude Sonnet 5 | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| DeepSWE | 5416 / 27Deep Thinking (With Tools) | 3723 / 27Thinking Medium (With Tools) | +17 |
Commonsense Reasoning
Gemini 3.5 Flash 1/1| Benchmark | Claude Sonnet 5 | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| SimpleBench | 57.9023 / 67Normal (No Tools) | 76.704 / 67Normal (No Tools) | -18.80 |
General Evaluation
Gemini 3.5 Flash 1/1| Benchmark | Claude Sonnet 5 | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| GPQA Diamond | 90.5333 / 226极高强度思考（无工具） | 92.8019 / 226Thinking High (No Tools) | -2.27 |
General Knowledge
Claude Sonnet 5 1/1| Benchmark | Claude Sonnet 5 | Gemini 3.5 Flash | Diff |
|---|---|---|---|
| HLE | 57.409 / 181极高强度思考（工具） | 40.2066 / 181Thinking High (With Tools) | +17.20 |
Specs
| Field | Claude Sonnet 5 | Gemini 3.5 Flash |
|---|---|---|
| Publisher | Anthropic | Google Deep Mind |
| Release date | 2026-06-30 | 2026-06-20 |
| Model type | Multimodal model | Multimodal model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1M |
| Max output | 128K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Sonnet 5 | Gemini 3.5 Flash |
|---|---|---|
| Text input | $2 / 1M tokens | $1.5 / 1M tokens |
| Text output | $10 / 1M tokens | $9 / 1M tokens |
| Cache read | $0.3 / 1M tokens | $0.15 / 1M tokens |
| Cache write | $3.75 / 1M tokens | Not public |
Summary
- Claude Sonnet 5leads in:AI Agent - Tool Usage (2/2), Math and Reasoning (2/2), Coding and Software Engineer (1/1), General Knowledge (1/1)
- Gemini 3.5 Flashleads in:Commonsense Reasoning (1/1), General Evaluation (1/1)
On average across the 8 shared benchmarks, Claude Sonnet 5 scores 3.17 higher.
Largest single-benchmark gap: SimpleBench — Claude Sonnet 5 57.90 vs Gemini 3.5 Flash 76.70 (-18.80).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.