Compare / head-to-head
Claude Opus 4.8vsGemini 3.7 Flash
Claude Opus 4.8 leads 3 of 5 shared benchmarks. Gemini 3.7 Flash is 6.7x cheaper per token. Gemini 3.7 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
3 – 2
Claude Opus 4.8 leads
Cheaper per token
Gemini 3.7 Flash
6.7x cheaper, input + output
Larger context
Gemini 3.7 Flash
1.0M tokens
Provider uptime (30d)
100% · 100%
Anthropic · Google
Claude Opus 4.8
Anthropic · released 2026-05-28
textvision
Gemini 3.7 Flash
Google · released 2026-08-13
textvisionaudio
Quality
Benchmark matrix
5 shared · 11 only Claude Opus 4.8 · 9 only Gemini 3.7 Flash| Benchmark | Claude Opus 4.8 | Gemini 3.7 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| GPQA Diamond | 93.6% ↗ | 94.8% ↗epoch | -1.2 pt | Gemini 3.7 Flash |
| FrontierMath Tier 4 v2 (Epoch AI run) | 56.1% ↗epoch | 36.6% ↗epoch | +19.5 pt | Claude Opus 4.8 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 80% ↗epoch | 71.6% ↗epoch | +8.4 pt | Claude Opus 4.8 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.3% ↗epoch | 97.2% ↗epoch | +1.1 pt | Claude Opus 4.8 |
| SimpleQA Verified | 53% ↗epoch | 69.2% ↗epoch | -16.2 pt | Gemini 3.7 Flash |
| Only Claude Opus 4.8 reports · 11 | ||||
| SWE-bench Verified | 88.6% ↗ | not reported | — | — |
| AIME 2026 | 100% ↗matharena ⚠ | not reported | — | — |
| Humanity's Last Exam (no tools) | 49.8% ↗ | not reported | — | — |
| LMArena Elo | 1452.7 ↗ | not reported | — | — |
| BrowseComp | 84.3% ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 57.9% ↗ | not reported | — | — |
| OSWorld-Verified | 83.4% ↗ | not reported | — | — |
| SWE-bench Multilingual | 84.4% ↗ | not reported | — | — |
| SWE-bench Multimodal | 38.4% ↗ | not reported | — | — |
| SWE-Bench Pro | 69.2% ↗ | not reported | — | — |
| Terminal-Bench 2.1 | 74.6% ↗ | not reported | — | — |
| Only Gemini 3.7 Flash reports · 9 | ||||
| Artificial Analysis Intelligence Index | not reported | 56 ↗ | — | — |
| Code Arena | not reported | 1588 ↗ | — | — |
| DeepSWE v1.1 | not reported | 65.3% ↗ | — | — |
| FrontierCode 1.1 | not reported | 43.6% ↗ | — | — |
| GDPVal-AA v2 | not reported | 1525 ↗ | — | — |
| HLE-Verified | not reported | 53.6% ↗ | — | — |
| OSWorld-2.0 | not reported | 47.9% ↗ | — | — |
| Terminal-bench 2.1 | not reported | 85.8% ↗ | — | — |
| Terminal-bench 3.0 | not reported | 14.9% ↗ | — | — |
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 4.8 minus Gemini 3.7 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 4.8 | Gemini 3.7 Flash | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Gemini 3.7 Flash |
| Max output | 128K tokens | 66K tokens | Claude Opus 4.8 |
| Input price / 1M | $5 ↗ | $0.75 ↗ | Gemini 3.7 Flash |
| Output price / 1M | $25 ↗ | $3.75 ↗ | Gemini 3.7 Flash |
| Cached input / 1M | $0.5 ↗ | $0.075 ↗ | Gemini 3.7 Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $4.5 | Gemini 3.7 Flash |
| Modalities | text · vision | text · vision · audio | Gemini 3.7 Flash |
| Released | 2026-05-28 | 2026-08-13 | — |
| Cited benchmark scores | 17 | 14 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Opus 4.8 vs …
Models sharing the most benchmarksMore matchups
Gemini 3.7 Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 4.8 and Gemini 3.7 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.