Claude Opus 4.6 vs Gemini 3.5 Flash
| Spec | Claude Opus 4.6 | Gemini 3.5 Flash |
|---|---|---|
| Respan Index | 44.9 (#56) | 44.3 (#58) |
| Blended price per 1M | $10 | $3.38 |
| Context window | 1M | 1.0M |
| Input / output per 1M | $5 / $25 | $1.5 / $9 |
| Max output | 128K | 66K |
| Input | text, vision | text, vision, audio |
| Released | 2026-02-05 | 2026-05-19 |
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 Opus 4.6 | Gemini 3.5 Flash |
|---|---|---|
| Coding | 29.0 Claude Opus 4.6 | 19.0 Gemini 3.5 Flash |
| Agents | 55.7 Claude Opus 4.6 | 49.7 Gemini 3.5 Flash |
| Reasoning | 42.7 Claude Opus 4.6 | 49.9 Gemini 3.5 Flash |
| Knowledge & language | 47.4 Claude Opus 4.6 | 65.6 Gemini 3.5 Flash |
| Human preference | 55.4 Claude Opus 4.6 | 54.0 Gemini 3.5 Flash |
Benchmarks both report
Claude Opus 4.6 leads on 13 of the 27 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Opus 4.6 | Gemini 3.5 Flash |
|---|---|---|
| LMArena Elo | 1503 | 1478 |
| LMArena WebDev (LMArena) | 1547 | 1500 |
| LMArena Vision (LMArena) | 1299 | 1282 |
| Chess Puzzles (Epoch AI) | 21% | 45% |
| APEX-Agents (Mercor) | 46.3% | 27.5% |
| EBR-bench (Epoch AI) | 12.7% | 4.8% |
| FrontierMath Tier 4 v2 (Epoch AI) | 26.8% | 26.8% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 66% | 62.8% |
| GPQA Diamond | 91.3% | 92.8% |
| LiveBench Agentic Coding (LiveBench) | 49% | 49% |
| LiveBench Coding (LiveBench) | 78.2% | 78.2% |
| LiveBench Data Analysis (LiveBench) | 69.9% | 64.9% |
| LiveBench Instruction Following (LiveBench) | 63.3% | 75.6% |
| LiveBench Language (LiveBench) | 83.3% | 84.6% |
| LiveBench Mathematics (LiveBench) | 89.3% | 88.2% |
| LiveBench Reasoning (LiveBench) | 88.7% | 82% |
| Mystery Game Puzzles (Epoch AI) | 25% | 32% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.4% | 95.6% |
| SAGE (Vals AI) | 51.6% | 49.9% |
| SimpleQA Verified | 47% | 66.2% |
| SWE-bench Verified (Epoch AI) | 78.7% | 79.3% |
| Vending-Bench 2 (Andon Labs) | 8017.59 | 5396.42 |
| WeirdML (Håvard Tveit Ihle) | 78% | 62.6% |
| AIME 2026 | 96.7% | 95% |
| SimpleBench (SimpleBench) | 67.6% | 76.7% |
| MCP Atlas | 59.5% | 83.6% |
| OSWorld-Verified | 72.7% | 78.4% |
FAQ
Is Claude Opus 4.6 better than Gemini 3.5 Flash?
Claude Opus 4.6 scores 44.9 on the Respan Index (#56), ahead of Gemini 3.5 Flash at 44.3 (#58). Claude Opus 4.6 leads on 13 of the 27 benchmarks both report.
Which is cheaper, Claude Opus 4.6 or Gemini 3.5 Flash?
Claude Opus 4.6 lists at $5 input and $25 output per 1M tokens; Gemini 3.5 Flash at $1.5 and $9. Gemini 3.5 Flash is 3.0x cheaper per token at list price.
Which has the larger context window?
Claude Opus 4.6 accepts 1M tokens and Gemini 3.5 Flash 1.0M tokens.
Compare other models
- vsClaude Opus 4.6 vs Claude Opus 4.5
- vsClaude Opus 4.7 vs Claude Opus 4.6
- vsGemini 3.5 Flash vs Gemini 2.5 Flash
- vsGemini 3.6 Flash vs Gemini 3.5 Flash
- vsGemini 3.5 Flash vs Claude Haiku 4.5
- vsGemini 4 Argon vs Gemini 3.5 Flash
- vsClaude Opus 4.6 vs GLM-5.3-Flash
- vsClaude Opus 4.6 vs Qwen3.8-Flash-Next
- vsClaude Opus 4.6 vs DeepSeek V4 Flash
- vsGemini 3.5 Flash vs Qwen3.8-Flash-Next
- vsGemini 3.5 Flash vs Mistral Large 4
- vsGemini 3.5 Flash vs Gemini 3.1 Pro Preview