Claude Sonnet 5.5 vs Gemini 3.1 Pro Preview
| Spec | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| Respan Index | 72.9 (#2) | 43.9 (#51) |
| Blended price per 1M | $2 | $2.25 |
| Context window | 1M | 1.0M |
| Input / output per 1M | $1 / $5 | $1 / $6 |
| Max output | 128K | 66K |
| Input | text, vision | text, vision, audio |
| Released | 2026-09-28 | 2026-02-19 |
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 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| Coding | 78.6 Claude Sonnet 5.5 | 15.6 Gemini 3.1 Pro Preview |
| Agents | 78.5 Claude Sonnet 5.5 | 53.6 Gemini 3.1 Pro Preview |
| Reasoning | 79.0 Claude Sonnet 5.5 | 46.2 Gemini 3.1 Pro Preview |
| Knowledge & language | 48.5 Claude Sonnet 5.5 | 72.5 Gemini 3.1 Pro Preview |
| Human preference | 60.2 Claude Sonnet 5.5 | 52.2 Gemini 3.1 Pro Preview |
Benchmarks both report
Claude Sonnet 5.5 leads on 20 of the 26 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| MirrorCode (Epoch AI) | 97.8% | 8.9% |
| SAGE 1.1 (Vals AI) | 88% | 83.2% |
| Chess Puzzles (Epoch AI) | 59% | 51% |
| LMArena Agent (LMArena) | 0.1384 | -0.0445 |
| LMArena Elo | 1477 | 1487 |
| LMArena WebDev (LMArena) | 1770 | 1447 |
| Vending-Bench 2 (Andon Labs) | 11165.28 | 3774.25 |
| LMArena Vision (LMArena) | 1265 | 1280 |
| APEX-Agents (Mercor) | 75.5% | 35.1% |
| FrontierMath Tier 4 v2 (Epoch AI) | 80.5% | 26.8% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 88.8% | 59.6% |
| Furniture Assembly (Epoch AI) | 75% | 26.7% |
| GPQA Diamond | 95.6% | 94.3% |
| LiveBench Agentic Coding (LiveBench) | 56.3% | 44.1% |
| LiveBench Coding (LiveBench) | 91.4% | 76.5% |
| LiveBench Data Analysis (LiveBench) | 78.6% | 78.5% |
| LiveBench Instruction Following (LiveBench) | 70.5% | 79.1% |
| LiveBench Language (LiveBench) | 83.4% | 85.4% |
| LiveBench Mathematics (LiveBench) | 96.7% | 91% |
| LiveBench Reasoning (LiveBench) | 91.6% | 84% |
| Mystery Game Puzzles (Epoch AI) | 65% | 34% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 95.6% |
| SAGE (Vals AI) | 51.8% | 48.7% |
| SimpleQA Verified | 46.5% | 73.5% |
| Terminal-Bench 4.0 (Vals AI) | 64.1% | 2.5% |
| SimpleBench (SimpleBench) | 75.9% | 79.6% |
FAQ
Is Claude Sonnet 5.5 better than Gemini 3.1 Pro Preview?
Claude Sonnet 5.5 scores 72.9 on the Respan Index (#2), ahead of Gemini 3.1 Pro Preview at 43.9 (#51). Claude Sonnet 5.5 leads on 20 of the 26 benchmarks both report.
Which is cheaper, Claude Sonnet 5.5 or Gemini 3.1 Pro Preview?
Claude Sonnet 5.5 lists at $1 input and $5 output per 1M tokens; Gemini 3.1 Pro Preview at $1 and $6. Claude Sonnet 5.5 is 1.1x cheaper per token at list price.
Which has the larger context window?
Claude Sonnet 5.5 accepts 1M tokens and Gemini 3.1 Pro Preview 1.0M tokens.
Compare other models
- vsClaude Sonnet 5.5 vs Gemini 3.8 Flash
- vsClaude Sonnet 5.5 vs Grok 4.7
- vsClaude Sonnet 5.5 vs Claude Opus 5.5
- vsClaude Sonnet 5.5 vs Claude Fable 5.1
- vsClaude Sonnet 5.5 vs GPT-6 Astra
- vsGemini 3.1 Pro Preview vs Qwen3.8-Flash-Next
- vsGemini 3.1 Pro Preview vs Qwen3.7-Max
- vsGemini 3.1 Pro Preview vs Gemini 3.6 Flash