Compare / head-to-head
DeepSeek V3vsLlama 4 Scout
DeepSeek V3 leads 2 of 2 shared benchmarks. Llama 4 Scout has the larger context window (10M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
DeepSeek V3 leads
Cheaper per token
—
list price, input + output
Larger context
Llama 4 Scout
10M tokens
Provider uptime (30d)
100% · —
DeepSeek · Meta
DeepSeek V3
DeepSeek · released 2024-12-26
text
- Context
- 128K
- Max out
- 8K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 8 · 7 core
Llama 4 Scout
Meta · released 2025-04-05
textvision
- Context
- 10M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 2 · 2 core
Quality
Benchmark matrix
2 shared · 5 only DeepSeek V3 · 0 only Llama 4 Scout| Benchmark | DeepSeek V3 | Llama 4 Scout | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 59.1% ↗ | 57.2% ↗ | +1.9 pt | DeepSeek V3 |
| MMLU-Pro | 75.9% ↗ | 74.3% ↗ | +1.6 pt | DeepSeek V3 |
| Only DeepSeek V3 reports · 5 | ||||
| SWE-bench Verified | 42% ↗ | not reported | — | — |
| MMLU | 88.5% ↗ | not reported | — | — |
| AIME 2025 | 25% ↗matharena | not reported | — | — |
| LMArena Elo | 1332.4 ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 15.8% ↗epoch | not reported | — | — |
| Only Llama 4 Scout reports · 0 | ||||
| Llama 4 Scout reports nothing DeepSeek V3 does not. | ||||
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 DeepSeek V3 minus Llama 4 Scout 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 | DeepSeek V3 | Llama 4 Scout | Edge |
|---|---|---|---|
| Context window | 128K tokens | 10M tokens | Llama 4 Scout |
| Max output | 8K tokens | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text · vision | Llama 4 Scout |
| Released | 2024-12-26 | 2025-04-05 | — |
| Cited benchmark scores | 8 | 2 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
DeepSeek V3 vs …
Models sharing the most benchmarksMore matchups
Llama 4 Scout vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3 and Llama 4 Scout on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.