DeepSeek V4 Pro (0813) vs Grok 4.7.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | DeepSeek V4 Pro (0813) | Grok 4.7 | Winner |
|---|---|---|---|
| League Score | 62.4 | 64.5 | Grok 4.7 |
| Coding (SWE-bench %) | 73.6 | — | — |
| Reasoning (GPQA %) | 90.1 | — | — |
| Context (tokens) | 1000000 | 500000 | DeepSeek V4 Pro (0813) |
| Speed (tok/s) | 99.4 | 87.6 | DeepSeek V4 Pro (0813) |
| Price (blended $/1M) | $1.98 | $3.00 | DeepSeek V4 Pro (0813) (cheaper) |
Tale of the tape
| Spec | DeepSeek V4 Pro (0813) | Grok 4.7 |
|---|---|---|
| Maker | DeepSeek | xAI (SpaceXAI) |
| Released | Apr 24, 2026 | Sep 21, 2026 |
| League Score | 62 | 64 |
| Context | 1,000,000 tokens | 500,000 tokens |
| Max output | 384,000 | — |
| $/1M input | $1.32 | $2.00 |
| $/1M output | $3.96 | $6.00 |
| Weights | Open | Closed |
| Speed | 99.4 t/s | 87.6 t/s |
Head-to-head benchmarks (shared only)
| Benchmark | DeepSeek V4 Pro (0813) | Grok 4.7 |
|---|---|---|
| No shared benchmark measurements yet — shown as not measured, never interpolated. | ||
Cost at three workloads
| Workload | DeepSeek V4 Pro (0813) | Grok 4.7 |
|---|---|---|
| Light — 1M in / 250K out | $2.31 | $3.50 |
| Standard — 10M in / 2.5M out | $23.10 | $35.00 |
| Long-context — 50M in / 5M out | $85.80 | $130.00 |
The pick
Pick DeepSeek V4 Pro (0813) if you need the bigger context window; you want the lower running cost; you want downloadable weights / self-hosting; coding is the priority.
Pick Grok 4.7 if you want the higher overall League Score.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which is better overall, DeepSeek V4 Pro (0813) or Grok 4.7?
Grok 4.7 leads on overall League Score, 64 to 62 — a gap of 2 points on a composite of sourced benchmarks. That is overall form, not every category: check the per-category verdicts before choosing.
Which is cheaper, DeepSeek V4 Pro (0813) or Grok 4.7?
DeepSeek V4 Pro (0813) is cheaper: $1.98 vs $3.00 blended per 1M tokens (3:1 input/output mix) — about 1.5x less per token.
Which has the bigger context window, DeepSeek V4 Pro (0813) or Grok 4.7?
DeepSeek V4 Pro (0813), with 1M of context against 500K for Grok 4.7.
Are DeepSeek V4 Pro (0813) and Grok 4.7 open source?
DeepSeek V4 Pro (0813) is open weights — it can be downloaded and self-hosted; Grok 4.7 is closed weights — API access only.