Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
Claude Sonnet 5 vs Gemini 3.5 Flash: benchmark scores, pricing & comparison.
Side-by-side Claude Sonnet 5 vs Gemini 3.5 Flash comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Rank #6 vs #15AskClash overall scores 83.1 vs 58.2.
Pricing $3.00/$15.0 vs $1.50/$9.00Input and output token prices per 1M tokens when published.
Proprietary vs ProprietaryAnthropic vs Google.
Claude Sonnet 5 vs Gemini 3.5 Flash benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Claude Sonnet 5 | Gemini 3.5 Flash |
|---|---|---|
| Overall Score | 83.1 | 58.2 |
| Leaderboard Rank | #6 | #15 |
| RWT | 9.0 | 7.0 |
| HLE | 57.4 | 40.2 |
| GPQA | — | 92.2 |
| IFEval | — | 76.3 |
| SWE-Pro | 63.2 | 55.1 |
| Terminal-Bench | 80.4 | 76.2 |
| OSWorld | 81.2 | 78.4 |
| MCP Atlas | — | 83.6 |
| Finance Agent | — | 57.9 |
| CharXiv | — | 84.2 |
| MMMU-Pro | — | 83.6 |
| ARC-AGI 2 | — | 72.1 |
| Tau2 | — | 95.3 |
| MRCR | — | 77.3 |
| Input Price (per 1M tokens) | $3.00 | $1.50 |
| Output Price (per 1M tokens) | $15.0 | $9.00 |
| Context Window | 1M | 1M |
| Benchmark Cells | 6 | 14 |
More Claude Sonnet 5 and Gemini 3.5 Flash comparisons
Explore how Claude Sonnet 5 and Gemini 3.5 Flash stack up against other top-ranked LLMs.
Sakana Fugu Ultra vs Claude Sonnet 5Sakana Fugu Ultra vs Gemini 3.5 FlashClaude Mythos Fable 5 vs Claude Sonnet 5Claude Mythos Fable 5 vs Gemini 3.5 FlashClaude Opus 4.8 vs Claude Sonnet 5Claude Opus 4.8 vs Gemini 3.5 FlashGLM-5.2 vs Claude Sonnet 5GLM-5.2 vs Gemini 3.5 FlashGPT-5.5 vs Claude Sonnet 5GPT-5.5 vs Gemini 3.5 Flash
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.