Compare / head-to-head
Claude Opus 4.5vs
Gemini 3 Flash Preview
Claude Opus 4.5 leads 13 of 22 shared benchmarks. Gemini 3 Flash 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
13 – 9
Claude Opus 4.5 leads
Cheaper per token
—
list price, input + output
Larger context
Gemini 3 Flash Preview
1.0M tokens
Providers
2 providers
Anthropic · Google
Claude Opus 4.5
Anthropic · released 2025-11-24
textvision
Gemini 3 Flash Preview
Google · released 2025-12-17
textvisionaudio
- Context
- 1.0M
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 34 · 12 core
Quality
Benchmark matrix
22 shared · 16 only Claude Opus 4.5 · 4 only Gemini 3 Flash Preview| Benchmark | Claude Opus 4.5 | Gemini 3 Flash Preview | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 22 | ||||
| SWE-bench Verified | 80.9% ↗ | 78% ↗ | +2.9 pt | Claude Opus 4.5 |
| GPQA Diamond | 87% ↗ | 90.4% ↗ | -3.4 pt | Gemini 3 Flash Preview |
| LMArena Elo | 1473.6 ↗ | 1472.7 ↗ | +0.9 | Claude Opus 4.5 |
| BALROG (BALROG) | 43.5% ↗ | 48.1% ↗ | -4.6 pt | Gemini 3 Flash Preview |
| Chess Puzzles (Epoch AI run) | 12% ↗epoch run | 40% ↗epoch run | -28 pt | Gemini 3 Flash Preview |
| FrontierMath Tier 4 v2 (Epoch AI run) | 4.9% ↗epoch run | 17.1% ↗epoch run | -12.2 pt | Gemini 3 Flash Preview |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 34.4% ↗epoch run | 51.2% ↗epoch run | -16.8 pt | Gemini 3 Flash Preview |
| GSO Opt@1 (GSO) | 24.5% ↗ | 7.8% ↗ | +16.7 pt | Claude Opus 4.5 |
| LMArena WebDev (LMArena) | 1493.3 ↗ | 1438.9 ↗ | +54.4 | Claude Opus 4.5 |
| Mystery Game Puzzles (Epoch AI run) | 22% ↗epoch run | 26% ↗epoch run | -4 pt | Gemini 3 Flash Preview |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 86.1% ↗epoch run | 95.6% ↗epoch run | -9.5 pt | Gemini 3 Flash Preview |
| SAGE (Vals AI) | 52.1% ↗ | 51.8% ↗ | +0.3 pt | Claude Opus 4.5 |
| SimpleBench (SimpleBench) | 62% ↗ | 61.1% ↗ | +0.9 pt | Claude Opus 4.5 |
| SimpleQA Verified | 45.7% ↗epoch run | 68.7% ↗ | -23 pt | Gemini 3 Flash Preview |
| SWE-bench Verified (Epoch AI run) | 76.7% ↗epoch run | 75.4% ↗epoch run | +1.3 pt | Claude Opus 4.5 |
| tau2-bench Airline (Sierra) | 84% ↗ | 82.5% ↗ | +1.5 pt | Claude Opus 4.5 |
| tau2-bench Banking Knowledge (Sierra) | 24.7% ↗ | 27.3% ↗ | -2.6 pt | Gemini 3 Flash Preview |
| tau2-bench Retail (Sierra) | 79.6% ↗ | 76.8% ↗ | +2.8 pt | Claude Opus 4.5 |
| tau2-bench Telecom (Sierra) | 92.3% ↗ | 91.2% ↗ | +1.1 pt | Claude Opus 4.5 |
| Terminal-Bench 2.0 | 59.3% ↗ | 47.6% ↗ | +11.7 pt | Claude Opus 4.5 |
| Vending-Bench 2 (Andon Labs) | 4967.06 ↗ | 3634.72 ↗ | +1332.3 | Claude Opus 4.5 |
| WeirdML (Håvard Tveit Ihle) | 63.7% ↗ | 61.6% ↗ | +2.1 pt | Claude Opus 4.5 |
| Only Claude Opus 4.5 reports · 16 | ||||
| ARC-AGI-2 (Verified) | 37.6% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 14.3% ↗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 | — | — |
| MCP Atlas | 62.3% ↗ | not reported | — | — |
| MMMLU | 90.8% ↗ | not reported | — | — |
| MMMU (validation) | 80.7% ↗ | not reported | — | — |
| OSWorld | 66.3% ↗ | not reported | — | — |
| τ2-bench (Retail) | 88.9% ↗ | not reported | — | — |
| τ2-bench (Telecom) | 98.2% ↗ | not reported | — | — |
| Only Gemini 3 Flash Preview reports · 4 | ||||
| AIME 2025 | not reported | 95.2% ↗ | — | — |
| Humanity's Last Exam (no tools) | not reported | 33.7% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1272.9 ↗ | — | — |
| MMMU-Pro | not reported | 81.2% ↗ | — | — |
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 Flash 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 Flash Preview | Edge |
|---|---|---|---|
| Context window | 200K tokens | 1.0M tokens | Gemini 3 Flash Preview |
| Max output | 64K tokens | 66K tokens | Gemini 3 Flash Preview |
| Input price / 1M | $5 ↗ | — | — |
| Output price / 1M | $25 ↗ | — | — |
| Cached input / 1M | $0.5 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | — | — |
| Modalities | text · vision | text · vision · audio | Gemini 3 Flash Preview |
| Released | 2025-11-24 | 2025-12-17 | — |
| Cited benchmark scores | 39 | 34 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 4.5 vs …
Models sharing the most benchmarksMore matchups
Gemini 3 Flash 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 Flash Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.