Claude Sonnet 5 vs Gemini 3.5 Flash
Claude Sonnet 5 wins on Overall, Coding; Gemini 3.5 Flash wins on Multimodal. Every numeric field is compared below, with a worked monthly-cost example and a pick rule for each use case.
Verdict at a glance
Choose Claude Sonnet 5 if you…
- Fast
- Moderately priced
- Anthropic quality
- Value flagship
- Best for: Daily tasks, Fast responses, Coding
Choose Gemini 3.5 Flash if you…
- Extremely fast
- Low price
- Native multimodal
- Built for scale
- Best for: Fast tasks, Multimodal, Low cost
Head-to-head aggregate scores
Scores are 0–100, aggregated from public benchmark information and independently weighted across three leaderboards. Rank is out of 22 tracked models.
Aggregated from public sources and independently weighted; methodology on the Terms page. Scores within 3 points are treated as statistically tied.
Specs & pricing — every field side by side
List API prices in USD per 1M tokens. The highlighted cell is the stronger value/capability on that row.
| Dimension | Claude Sonnet 5 | Gemini 3.5 Flash | Verdict |
|---|---|---|---|
| Vendor | Anthropic (US) | Google (US) | Different vendors |
| Released | 2026.06 | 2026.07 | Gemini 3.5 Flash is newer |
| Overall (rank) | 71 · #12 | 69 · #14 | Claude Sonnet 5 +2 |
| Coding | 73 · #10 | 64 · #17 | Claude Sonnet 5 +9 |
| Multimodal | 76 · #14 | 86 · #7 | Gemini 3.5 Flash +10 |
| Context window | 1M | 1M | Tie |
| Max output | 128K | 128K | Tie |
| Effective-context | 95 | 88 | Claude Sonnet 5 more reliable |
| Input $/1M | $3 | $1.5 | Gemini 3.5 Flash cheaper |
| Output $/1M | $15 | $9 | Gemini 3.5 Flash cheaper |
| Cache discount | 90% off | none | Claude Sonnet 5 deeper |
| Speed | ~65 tok/s | ~80 tok/s | Gemini 3.5 Flash faster |
| TTFT | 0.5s | 0.3s | Gemini 3.5 Flash snappier |
| Function calling | 88 | 75 | Claude Sonnet 5 ahead |
| Refusal rate | ~8% | ~10% | Claude Sonnet 5 less restrictive |
| English | 90 | 85 | Claude Sonnet 5 |
| Chinese | 78 | 72 | Claude Sonnet 5 |
| Modalities | text, image | text, image, audio, video | different coverage |
| Open weights | No | No | Both closed |
| Fine-tuning | No | Yes | |
| Free tier | No free tier | Gemini App free; API free tier | |
| SOC2 / no-train | yes / yes | yes / yes | |
| Private deployment | No | No | Neither |
Fields drawn from vendor public documentation and the Modelspectra 22-model dataset; speed varies with network, concurrency and prompt length. Verify current pricing before purchase.
Dimension-by-dimension analysis
Reasoning & overall intelligence
Claude Sonnet 5 leads the overall aggregate by 2 points (71 vs 69). That is a meaningful, not marginal, edge on hard, multi-step reasoning, while Gemini 3.5 Flash remains a strong generalist that is not out of its depth on routine work.
Agentic coding
This is a modest gap: Claude Sonnet 5 scores 73 against 64. On multi-file edits, SWE-style tickets and long-horizon agent loops Claude Sonnet 5 needs fewer correction turns; Gemini 3.5 Flash is still competent for scripts and assisted completion but trails as task complexity rises.
Multimodal
Gemini 3.5 Flash leads multimodal 86 vs 76. A concrete modality difference: Gemini 3.5 Flash additionally handles audio, video.
Speed & latency
Gemini 3.5 Flash is faster in interactive use: ~80 tok/s with 0.3s TTFT versus ~65 tok/s with 0.5s TTFT (about 1.2× the throughput). For conversational UIs where perceived responsiveness drives retention, that edge is a real product factor even when raw reasoning is lower.
Context: window vs usable recall
Nominal windows are 1M for Claude Sonnet 5 and 1M for Gemini 3.5 Flash. Effective-context scores point the same way as window size — Claude Sonnet 5 is ahead on usable recall (95 vs 88), so prefer it for long-document work where details cannot be missed.
Price & total cost
Gemini 3.5 Flash is the cheaper API at $1.5/$9 versus Claude Sonnet 5 at $3/$15 per 1M input/output tokens — list input is about 2.0× lower. Cache discounts (Claude Sonnet 5 90%) shift the effective bill, worked out below.
Chinese vs English
English: Claude Sonnet 5 90 vs Gemini 3.5 Flash 85. Chinese: 78 vs 72. Both are US-based models; for Chinese-first workloads also compare domestic models on the leaderboard.
Tool use & ecosystem
Function-calling score: Claude Sonnet 5 88 vs Gemini 3.5 Flash 75, so Claude Sonnet 5 has the edge on structured tool use. Fine-tuning is available from Gemini 3.5 Flash. Factor in existing SDK/plugin familiarity — switching cost often outweighs a few-point tool-use gap.
Cost worked example — same workload, real token math
Assume a production workload of 100M input + 30M output tokens per month, with 90% of input tokens served from cache. Figures use public list prices.
| Scenario · per month | Claude Sonnet 5 | Gemini 3.5 Flash | Gap |
|---|---|---|---|
| List priceno cache applied | $750100M in × $3 + 30M out × $15 | $420100M in × $1.5 + 30M out × $9 | 1.79×gap |
| With caching90% of inputs cache-hit | $50790M cached in × $0.3 + 10M in × $3 + 30M out × $15 | $420no published cache discount | 1.21×gap |
Illustrative model; your input/output mix and cache-hit ratio change the result. Prices are list rates before any enterprise agreement.