Compare / head-to-head
Claude Opus 5vsGemini 3.5 Flash
Claude Opus 5 leads 4 of 5 shared benchmarks. Gemini 3.5 Flash is 2.9x cheaper per token. Gemini 3.5 Flash 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 – 1
Claude Opus 5 leads
Cheaper per token
Gemini 3.5 Flash
2.9x cheaper, input + output
Larger context
Gemini 3.5 Flash
1.0M tokens
Provider uptime (30d)
100% · 100%
Anthropic · Google
Claude Opus 5
Anthropic · released 2026-07-24
textvision
Gemini 3.5 Flash
Google · released 2026-05-19
textvisionaudio
Quality
Benchmark matrix
5 shared · 4 only Claude Opus 5 · 10 only Gemini 3.5 Flash| Benchmark | Claude Opus 5 | Gemini 3.5 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| GPQA Diamond | 93.9% ↗epoch | 92.8% ↗epoch | +1.1 pt | Claude Opus 5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 73.2% ↗epoch | 26.8% ↗epoch | +46.4 pt | Claude Opus 5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 85.6% ↗epoch | 62.8% ↗epoch | +22.8 pt | Claude Opus 5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.9% ↗epoch | 95.6% ↗epoch | +3.3 pt | Claude Opus 5 |
| SimpleQA Verified | 59.9% ↗epoch | 66.2% ↗epoch | -6.3 pt | Gemini 3.5 Flash |
| Only Claude Opus 5 reports · 4 | ||||
| Humanity's Last Exam (no tools) | 56.6% ↗ | not reported | — | — |
| CursorBench 3.2.0 | 70% ↗ | not reported | — | — |
| GDPval-AA v2 | 1824 ↗ | not reported | — | — |
| Terminal-Bench Science 0.1 | 29% ↗ | not reported | — | — |
| Only Gemini 3.5 Flash reports · 10 | ||||
| AIME 2026 | not reported | 95% ↗matharena ⚠ | — | — |
| ARC-AGI-2 | not reported | 72.1% ↗ | — | — |
| GDPVal-AA | not reported | 1656 ↗ | — | — |
| Humanity's Last Exam (full set, text + MM) | not reported | 40.2% ↗ | — | — |
| MCP Atlas | not reported | 83.6% ↗ | — | — |
| MMMU-Pro | not reported | 83.6% ↗ | — | — |
| OSWorld-Verified | not reported | 78.4% ↗ | — | — |
| SWE-Bench Pro (Public) | not reported | 55.1% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 79.3% ↗epoch | — | — |
| Terminal-bench 2.1 | not reported | 76.2% ↗ | — | — |
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 5 minus Gemini 3.5 Flash 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 | Gemini 3.5 Flash | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Gemini 3.5 Flash |
| Max output | 128K tokens | 66K tokens | Claude Opus 5 |
| Input price / 1M | $5 ↗ | $1.5 ↗ | Gemini 3.5 Flash |
| Output price / 1M | $25 ↗ | $9 ↗ | Gemini 3.5 Flash |
| Cached input / 1M | $0.5 ↗ | $0.15 ↗ | Gemini 3.5 Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $10.5 | Gemini 3.5 Flash |
| Modalities | text · vision | text · vision · audio | Gemini 3.5 Flash |
| Released | 2026-07-24 | 2026-05-19 | — |
| Cited benchmark scores | 9 | 15 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Opus 5 vs …
Models sharing the most benchmarksMore matchups
Gemini 3.5 Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 5 and Gemini 3.5 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.