Compare / head-to-head
Claude Opus 4.5vs
Gemini 3 Pro Preview
Gemini 3 Pro Preview leads 9 of 13 shared benchmarks. Gemini 3 Pro Preview is 2.1x 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 – 9
Gemini 3 Pro Preview leads
Cheaper per token
Gemini 3 Pro Preview
2.1x cheaper, input + output
Larger context
Gemini 3 Pro Preview
1.0M tokens
Providers
2 providers
Anthropic · Google
Claude Opus 4.5
Anthropic · released 2025-11-24
textvision
Gemini 3 Pro Preview
Google · released 2025-11-18
textvisionaudiovideo
Quality
Benchmark matrix
13 shared · 25 only Claude Opus 4.5 · 11 only Gemini 3 Pro Preview| Benchmark | Claude Opus 4.5 | Gemini 3 Pro Preview | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 13 | ||||
| SWE-bench Verified | 80.9% ↗ | 76.2% ↗ | +4.7 pt | Claude Opus 4.5 |
| GPQA Diamond | 87% ↗ | 91.9% ↗ | -4.9 pt | Gemini 3 Pro Preview |
| BALROG (BALROG) | 43.5% ↗ | 58.1% ↗ | -14.6 pt | Gemini 3 Pro Preview |
| Chess Puzzles (Epoch AI run) | 12% ↗epoch run | 31% ↗epoch run | -19 pt | Gemini 3 Pro Preview |
| GSO Opt@1 (GSO) | 24.5% ↗ | 17.7% ↗ | +6.8 pt | Claude Opus 4.5 |
| MMMLU | 90.8% ↗ | 91.8% ↗ | -1 pt | Gemini 3 Pro Preview |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 86.1% ↗epoch run | 91.4% ↗epoch run | -5.3 pt | Gemini 3 Pro Preview |
| SAGE (Vals AI) | 52.1% ↗ | 47.6% ↗ | +4.5 pt | Claude Opus 4.5 |
| SimpleBench (SimpleBench) | 62% ↗ | 76.4% ↗ | -14.4 pt | Gemini 3 Pro Preview |
| SimpleQA Verified | 45.7% ↗epoch run | 72.1% ↗ | -26.4 pt | Gemini 3 Pro Preview |
| SWE-bench Verified (Epoch AI run) | 76.7% ↗epoch run | 72.9% ↗epoch run | +3.8 pt | Claude Opus 4.5 |
| Vending-Bench 2 (Andon Labs) | 4967.06 ↗ | 5478.16 ↗ | -511.1 | Gemini 3 Pro Preview |
| WeirdML (Håvard Tveit Ihle) | 63.7% ↗ | 69.9% ↗ | -6.2 pt | Gemini 3 Pro Preview |
| Only Claude Opus 4.5 reports · 25 | ||||
| LMArena Elo | 1473.6 ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 37.6% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 14.3% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 4.9% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 34.4% ↗epoch run | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 28.3% ↗epoch run | not reported | — | — |
| LiveBench Agentic Coding (LiveBench) | 39.7% ↗ | not reported | — | — |
| LiveBench Coding (LiveBench) | 79.7% ↗ | not reported | — | — |
| LiveBench Data Analysis (LiveBench) | 74.4% ↗ | not reported | — | — |
| LiveBench Instruction Following (LiveBench) | 62.5% ↗ | not reported | — | — |
| LiveBench Language (LiveBench) | 81.3% ↗ | not reported | — | — |
| LiveBench Mathematics (LiveBench) | 90.4% ↗ | not reported | — | — |
| LiveBench Reasoning (LiveBench) | 80.1% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1493.3 ↗ | not reported | — | — |
| MCP Atlas | 62.3% ↗ | not reported | — | — |
| MMMU (validation) | 80.7% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 22% ↗epoch run | not reported | — | — |
| OSWorld | 66.3% ↗ | not reported | — | — |
| tau2-bench Airline (Sierra) | 84% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 24.7% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 79.6% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 92.3% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 59.3% ↗ | not reported | — | — |
| τ2-bench (Retail) | 88.9% ↗ | not reported | — | — |
| τ2-bench (Telecom) | 98.2% ↗ | not reported | — | — |
| Only Gemini 3 Pro Preview reports · 11 | ||||
| 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% ↗ | — | — |
| CharXiv Reasoning | not reported | 81.4% ↗ | — | — |
| Humanity's Last Exam (with search and code execution) | not reported | 45.8% ↗ | — | — |
| MathArena Apex | not reported | 23.4% ↗ | — | — |
| MMMU-Pro | not reported | 81% ↗ | — | — |
| Terminal-Bench 2.0 (Terminus-2 agent) | not reported | 54.2% ↗ | — | — |
| Video-MMMU | not reported | 87.6% ↗ | — | — |
| 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 4.5 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 4.5 | Gemini 3 Pro Preview | Edge |
|---|---|---|---|
| Context window | 200K tokens | 1.0M tokens | Gemini 3 Pro Preview |
| Max output | 64K tokens | 66K tokens | Gemini 3 Pro Preview |
| Input price / 1M | $5 ↗ | $2 ↗ | Gemini 3 Pro Preview |
| Output price / 1M | $25 ↗ | $12 ↗ | Gemini 3 Pro Preview |
| Cached input / 1M | $0.5 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $14 | Gemini 3 Pro Preview |
| Modalities | text · vision | text · vision · audio · video | Gemini 3 Pro Preview |
| Released | 2025-11-24 | 2025-11-18 | — |
| Cited benchmark scores | 39 | 25 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 4.5 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 4.5 and Gemini 3 Pro Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.