Compare / head-to-head
Claude Opus 4.8vsDeepSeek V4 Pro
Claude Opus 4.8 leads 7 of 9 shared benchmarks. DeepSeek V4 Pro is 23x cheaper per token. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
7 – 2
Claude Opus 4.8 leads
Cheaper per token
DeepSeek V4 Pro
23x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100% · 100%
Anthropic · DeepSeek
Claude Opus 4.8
Anthropic · released 2026-05-28
textvision
DeepSeek V4 Pro
DeepSeek · released 2026-08-13
text
Quality
Benchmark matrix
9 shared · 7 only Claude Opus 4.8 · 2 only DeepSeek V4 Pro| Benchmark | Claude Opus 4.8 | DeepSeek V4 Pro | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 9 | ||||
| GPQA Diamond | 93.6% ↗ | 90.9% ↗epoch | +2.7 pt | Claude Opus 4.8 |
| AIME 2026 | 100% ↗matharena ⚠ | 96.7% ↗matharena ⚠ | +3.3 pt | Claude Opus 4.8 |
| LMArena Elo | 1452.7 ↗ | 1450.6 ↗ | +2.1 | Claude Opus 4.8 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 56.1% ↗epoch | 2.4% ↗epoch | +53.7 pt | Claude Opus 4.8 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 80% ↗epoch | 45.3% ↗epoch | +34.7 pt | Claude Opus 4.8 |
| Humanity's Last Exam (with tools) | 57.9% ↗ | 60% ↗ | -2.1 pt | DeepSeek V4 Pro |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.3% ↗epoch | 96.7% ↗epoch | +1.6 pt | Claude Opus 4.8 |
| SimpleQA Verified | 53% ↗epoch | 47% ↗epoch | +6 pt | Claude Opus 4.8 |
| Terminal-Bench 2.1 | 74.6% ↗ | 87.9% ↗ | -13.3 pt | DeepSeek V4 Pro |
| Only Claude Opus 4.8 reports · 7 | ||||
| SWE-bench Verified | 88.6% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 49.8% ↗ | not reported | — | — |
| BrowseComp | 84.3% ↗ | 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 | — | — |
| Only DeepSeek V4 Pro reports · 2 | ||||
| DeepSWE v1.1 | not reported | 62.7% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 77.6% ↗epoch | — | — |
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 DeepSeek V4 Pro 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 | DeepSeek V4 Pro | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 128K tokens | 384K tokens | DeepSeek V4 Pro |
| Input price / 1M | $5 ↗ | $0.435 ↗ | DeepSeek V4 Pro |
| Output price / 1M | $25 ↗ | $0.87 ↗ | DeepSeek V4 Pro |
| Cached input / 1M | $0.5 ↗ | $0.004 ↗ | DeepSeek V4 Pro |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $1.31 | DeepSeek V4 Pro |
| Modalities | text · vision | text | Claude Opus 4.8 |
| Released | 2026-05-28 | 2026-08-13 | — |
| Cited benchmark scores | 17 | 11 | — |
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
DeepSeek V4 Pro 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 DeepSeek V4 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.