Claude Sonnet 4.6 vs Gemini 3 Pro Preview
| Spec | Claude Sonnet 4.6 | Gemini 3 Pro Preview |
|---|---|---|
| Respan Index | 37.3 (#65) | 39.3 (#64) |
| Blended price per 1M | $6 | $4.5 |
| Context window | 1M | 1.0M |
| Input / output per 1M | $3 / $15 | $2 / $12 |
| Max output | 128K | 66K |
| Input | text, vision | text, vision, audio, video |
| Released | 2026-02-17 | 2025-11-18 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude Sonnet 4.6 | Gemini 3 Pro Preview |
|---|---|---|
| Coding | 14.6 Claude Sonnet 4.6 | 17.6 Gemini 3 Pro Preview |
| Agents | 51.0 Claude Sonnet 4.6 | 47.0 Gemini 3 Pro Preview |
| Reasoning | 36.8 Claude Sonnet 4.6 | 41.9 Gemini 3 Pro Preview |
| Knowledge & language | 35.7 Claude Sonnet 4.6 | 48.1 Gemini 3 Pro Preview |
| Human preference | 54.0 Claude Sonnet 4.6 | 52.1 Gemini 3 Pro Preview |
Benchmarks both report
Gemini 3 Pro Preview leads on 10 of the 14 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro Preview |
|---|---|---|
| Chess Puzzles (Epoch AI) | 23% | 31% |
| LMArena Elo | 1472 | 1485 |
| LMArena WebDev (LMArena) | 1523 | 1440 |
| LMArena Vision (LMArena) | 1275 | 1289 |
| GPQA Diamond | 89.9% | 91.9% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 85.8% | 91.4% |
| SAGE (Vals AI) | 46.6% | 47.6% |
| SimpleQA Verified | 35.5% | 72.1% |
| SWE-bench Verified (Epoch AI) | 75.2% | 72.9% |
| Vending-Bench 2 (Andon Labs) | 7204.14 | 5478.16 |
| WeirdML (Håvard Tveit Ihle) | 66.1% | 69.9% |
| Humanity's Last Exam (no tools) | 33.2% | 37.5% |
| MMMLU | 89.3% | 91.8% |
| SWE-bench Verified | 79.6% | 76.2% |
FAQ
Is Claude Sonnet 4.6 better than Gemini 3 Pro Preview?
Gemini 3 Pro Preview scores 39.3 on the Respan Index (#64), ahead of Claude Sonnet 4.6 at 37.3 (#65). Gemini 3 Pro Preview leads on 10 of the 14 benchmarks both report.
Which is cheaper, Claude Sonnet 4.6 or Gemini 3 Pro Preview?
Claude Sonnet 4.6 lists at $3 input and $15 output per 1M tokens; Gemini 3 Pro Preview at $2 and $12. Gemini 3 Pro Preview is 1.3x cheaper per token at list price.
Which has the larger context window?
Claude Sonnet 4.6 accepts 1M tokens and Gemini 3 Pro Preview 1.0M tokens.