Gemini 3.1 Pro vs Claude Sonnet 5
Gemini 3.1 Pro wins on Overall, Coding, 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 Gemini 3.1 Pro if you…
- Native audio and video
- Strong scientific computing
- Largest 2M context
- Search integration
- Best for: Multimodal, Scientific reasoning, Audio & video
Choose Claude Sonnet 5 if you…
- Fast
- Moderately priced
- Anthropic quality
- Value flagship
- Best for: Daily tasks, Fast responses, Coding
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 | Gemini 3.1 Pro | Claude Sonnet 5 | Verdict |
|---|---|---|---|
| Vendor | Google (US) | Anthropic (US) | Different vendors |
| Released | 2026.05 | 2026.06 | Claude Sonnet 5 is newer |
| Overall (rank) | 83 · #3 | 71 · #12 | Gemini 3.1 Pro +12 |
| Coding | 74 · #9 | 73 · #10 | Gemini 3.1 Pro +1 |
| Multimodal | 92 · #2 | 76 · #14 | Gemini 3.1 Pro +16 |
| Context window | 2M | 1M | Gemini 3.1 Pro larger |
| Max output | 128K | 128K | Tie |
| Effective-context | 92 | 95 | Claude Sonnet 5 more reliable |
| Input $/1M | $2 | $3 | Gemini 3.1 Pro cheaper |
| Output $/1M | $12 | $15 | Gemini 3.1 Pro cheaper |
| Cache discount | none | 90% off | Claude Sonnet 5 deeper |
| Speed | ~60 tok/s | ~65 tok/s | Claude Sonnet 5 faster |
| TTFT | 0.7s | 0.5s | Claude Sonnet 5 snappier |
| Function calling | 78 | 88 | Claude Sonnet 5 ahead |
| Refusal rate | ~12% | ~8% | Claude Sonnet 5 less restrictive |
| English | 90 | 90 | Tie |
| Chinese | 75 | 78 | Claude Sonnet 5 |
| Modalities | text, image, audio, video | text, image | different coverage |
| Open weights | No | No | Both closed |
| Fine-tuning | Yes | No | |
| Free tier | Gemini App free with limited quota; API free tier available | No 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
Gemini 3.1 Pro leads the overall aggregate by 12 points (83 vs 71). That is a meaningful, not marginal, edge on hard, multi-step reasoning, while Claude Sonnet 5 remains a strong generalist that is not out of its depth on routine work.
Agentic coding
This is a modest gap: Gemini 3.1 Pro scores 74 against 73. On multi-file edits, SWE-style tickets and long-horizon agent loops Gemini 3.1 Pro needs fewer correction turns; Claude Sonnet 5 is still competent for scripts and assisted completion but trails as task complexity rises.
Multimodal
Gemini 3.1 Pro leads multimodal 92 vs 76. A concrete modality difference: Gemini 3.1 Pro additionally handles audio, video.
Speed & latency
Claude Sonnet 5 is faster in interactive use: ~65 tok/s with 0.5s TTFT versus ~60 tok/s with 0.7s TTFT (about 1.1× 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 2M for Gemini 3.1 Pro and 1M for Claude Sonnet 5. Crucially, the larger nominal window does not win on usable recall: Gemini 3.1 Pro advertises 2M but Claude Sonnet 5 scores higher on effective-context (95 vs 92), i.e. it actually retains more of what it was given.
Price & total cost
Gemini 3.1 Pro is the cheaper API at $2/$12 versus Claude Sonnet 5 at $3/$15 per 1M input/output tokens — list input is about 1.5× lower. Cache discounts (Claude Sonnet 5 90%) shift the effective bill, worked out below.
Chinese vs English
English: Gemini 3.1 Pro 90 vs Claude Sonnet 5 90. Chinese: 75 vs 78. Both are US-based models; for Chinese-first workloads also compare domestic models on the leaderboard.
Tool use & ecosystem
Function-calling score: Gemini 3.1 Pro 78 vs Claude Sonnet 5 88, so Claude Sonnet 5 has the edge on structured tool use. Fine-tuning is available from Gemini 3.1 Pro. 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 | Gemini 3.1 Pro | Claude Sonnet 5 | Gap |
|---|---|---|---|
| List priceno cache applied | $560100M in × $2 + 30M out × $12 | $750100M in × $3 + 30M out × $15 | 1.34×gap |
| With caching90% of inputs cache-hit | $560no published cache discount | $50790M cached in × $0.3 + 10M in × $3 + 30M out × $15 | 1.10×gap |
Illustrative model; your input/output mix and cache-hit ratio change the result. Prices are list rates before any enterprise agreement.