Compare / head-to-head
Claude Opus 5.5vs
Gemini 3 Pro Preview
Claude Opus 5.5 leads 4 of 6 shared benchmarks. Gemini 3 Pro Preview is 1.7x cheaper per token. Gemini 3 Pro Preview has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
4 – 2
Claude Opus 5.5 leads
Cheaper per token
Gemini 3 Pro Preview
1.7x cheaper, input + output
Larger context
Gemini 3 Pro Preview
1.0M tokens
Providers
2 providers
Anthropic · Google
Claude Opus 5.5
Anthropic · released 2026-09-22
textvision
Gemini 3 Pro Preview
Google · released 2025-11-18
textvisionaudiovideo
Quality
Benchmark matrix
6 shared · 28 only Claude Opus 5.5 · 18 only Gemini 3 Pro Preview| Benchmark | Claude Opus 5.5 | Gemini 3 Pro Preview | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 6 | ||||
| GPQA Diamond | 90.6% ↗epoch run | 91.9% ↗ | -1.3 pt | Gemini 3 Pro Preview |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 91.4% ↗epoch run | +8.6 pt | Claude Opus 5.5 |
| SAGE (Vals AI) | 45.8% ↗ | 47.6% ↗ | -1.8 pt | Gemini 3 Pro Preview |
| SimpleBench (SimpleBench) | 88.4% ↗ | 76.4% ↗ | +12 pt | Claude Opus 5.5 |
| SimpleQA Verified | 72.2% ↗epoch run | 72.1% ↗ | +0.1 pt | Claude Opus 5.5 |
| Vending-Bench 2 (Andon Labs) | 9235.25 ↗ | 5478.16 ↗ | +3757.1 | Claude Opus 5.5 |
| Only Claude Opus 5.5 reports · 28 | ||||
| LMArena Elo | 1503.7 ↗ | not reported | — | — |
| APEX-Agents (Mercor) | 73.5% ↗ | not reported | — | — |
| AutomationBench 1.0.6 | 40% ↗ | not reported | — | — |
| Chartography (with tools) | 89% ↗ | not reported | — | — |
| CursorBench 4.0 | 57.8% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 71.4% ↗epoch run | not reported | — | — |
| FrontierCode v1.1 (Main) | 54.4% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 95% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 91.2% ↗epoch run | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 62.3% ↗ | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 83.3% ↗epoch run | not reported | — | — |
| GDPval-AA v2.1 | 1846 ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 67.7% ↗ | not reported | — | — |
| LiveBench Agentic Coding (LiveBench) | 71.7% ↗ | not reported | — | — |
| LiveBench Coding (LiveBench) | 89.3% ↗ | not reported | — | — |
| LiveBench Data Analysis (LiveBench) | 80.3% ↗ | not reported | — | — |
| LiveBench Instruction Following (LiveBench) | 67% ↗ | not reported | — | — |
| LiveBench Language (LiveBench) | 86.3% ↗ | not reported | — | — |
| LiveBench Mathematics (LiveBench) | 97.1% ↗ | not reported | — | — |
| LiveBench Reasoning (LiveBench) | 92.2% ↗ | not reported | — | — |
| LMArena Agent (LMArena) | 0.1382 ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1815.4 ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 77.4% ↗epoch run | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 71% ↗epoch run | not reported | — | — |
| OSWorld 2.0 (partial) | 81.8% ↗ | not reported | — | — |
| Terminal-Bench 4.0 | 66.4% ↗ | not reported | — | — |
| Terminal-Bench 4.0 (Vals AI) | 65.2% ↗ | not reported | — | — |
| Terminal-Bench Science 0.1 | 58.7% ↗ | not reported | — | — |
| Only Gemini 3 Pro Preview reports · 18 | ||||
| SWE-bench Verified | not reported | 76.2% ↗ | — | — |
| AIME 2025 | not reported | 95% ↗ | — | — |
| Humanity's Last Exam (no tools) | not reported | 37.5% ↗ | — | — |
| AIME 2025 (with code execution) | not reported | 100% ↗ | — | — |
| ARC-AGI-2 (ARC Prize Verified) | not reported | 31.1% ↗ | — | — |
| BALROG (BALROG) | not reported | 58.1% ↗ | — | — |
| CharXiv Reasoning | not reported | 81.4% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 31% ↗epoch run | — | — |
| GSO Opt@1 (GSO) | not reported | 17.7% ↗ | — | — |
| Humanity's Last Exam (with search and code execution) | not reported | 45.8% ↗ | — | — |
| MathArena Apex | not reported | 23.4% ↗ | — | — |
| MMMLU | not reported | 91.8% ↗ | — | — |
| MMMU-Pro | not reported | 81% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 72.9% ↗epoch run | — | — |
| Terminal-Bench 2.0 (Terminus-2 agent) | not reported | 54.2% ↗ | — | — |
| Video-MMMU | not reported | 87.6% ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 69.9% ↗ | — | — |
| τ2-bench | not reported | 85.4% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Opus 5.5 minus Gemini 3 Pro Preview in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude Opus 5.5 | Gemini 3 Pro Preview | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Gemini 3 Pro Preview |
| Max output | 128K tokens | 66K tokens | Claude Opus 5.5 |
| Input price / 1M | $4 ↗ | $2 ↗ | Gemini 3 Pro Preview |
| Output price / 1M | $20 ↗ | $12 ↗ | Gemini 3 Pro Preview |
| Cached input / 1M | $0.2 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $24 | $14 | Gemini 3 Pro Preview |
| Modalities | text · vision | text · vision · audio · video | Gemini 3 Pro Preview |
| Released | 2026-09-22 | 2025-11-18 | — |
| Cited benchmark scores | 34 | 25 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 5.5 vs …
Models sharing the most benchmarksMore matchups
Gemini 3 Pro Preview vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 5.5 and Gemini 3 Pro Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.