Compare / head-to-head
DeepSeek V4 ProvsLongCat Flash Chat
DeepSeek V4 Pro leads 2 of 2 shared benchmarks. DeepSeek V4 Pro has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
DeepSeek V4 Pro leads
Cheaper per token
—
list price, input + output
Larger context
DeepSeek V4 Pro
1M tokens
Provider uptime (30d)
100% · —
DeepSeek · Meituan LongCat
DeepSeek V4 Pro
DeepSeek · released 2026-08-13
text
LongCat Flash Chat
Meituan LongCat · released 2025-09-01
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 31 · 9 core
Quality
Benchmark matrix
2 shared · 9 only DeepSeek V4 Pro · 29 only LongCat Flash Chat| Benchmark | DeepSeek V4 Pro | LongCat Flash Chat | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 90.9% ↗epoch | 73.23% ↗ | +17.7 pt | DeepSeek V4 Pro |
| LMArena Elo | 1450.6 ↗ | 1422.9 ↗ | +27.7 | DeepSeek V4 Pro |
| Only DeepSeek V4 Pro reports · 9 | ||||
| AIME 2026 | 96.7% ↗matharena ⚠ | not reported | — | — |
| DeepSWE v1.1 | 62.7% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 45.3% ↗epoch | not reported | — | — |
| Humanity's Last Exam (with tools) | 60% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 96.7% ↗epoch | not reported | — | — |
| SimpleQA Verified | 47% ↗epoch | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 77.6% ↗epoch | not reported | — | — |
| Terminal-Bench 2.1 | 87.9% ↗ | not reported | — | — |
| Only LongCat Flash Chat reports · 29 | ||||
| SWE-bench Verified | not reported | 60.4% ↗ | — | — |
| MMLU | not reported | 89.71% ↗ | — | — |
| MMLU-Pro | not reported | 82.68% ↗ | — | — |
| AIME 2025 | not reported | 61.25% ↗ | — | — |
| AceBench | not reported | 76.1% ↗ | — | — |
| AIME 2024 | not reported | 70.42% ↗ | — | — |
| ArenaHard-V2 | not reported | 86.5% ↗ | — | — |
| BeyondAIME | not reported | 43% ↗ | — | — |
| C-Eval | not reported | 90.44% ↗ | — | — |
| CMMLU | not reported | 84.34% ↗ | — | — |
| COLLIE | not reported | 57.1% ↗ | — | — |
| DROP | not reported | 79.06% ↗ | — | — |
| GraphWalks-128k | not reported | 51.05% ↗ | — | — |
| HumanEval+ | not reported | 88.41% ↗ | — | — |
| IFEval | not reported | 89.65% ↗ | — | — |
| LiveCodeBench | not reported | 48.02% ↗ | — | — |
| MATH500 | not reported | 96.4% ↗ | — | — |
| MBPP+ | not reported | 79.63% ↗ | — | — |
| Meeseeks-zh | not reported | 43.03% ↗ | — | — |
| Safety: Criminal | not reported | 91.24% ↗ | — | — |
| Safety: Harmful | not reported | 83.98% ↗ | — | — |
| Safety: Misinformation | not reported | 81.72% ↗ | — | — |
| Safety: Privacy | not reported | 93.98% ↗ | — | — |
| Tau2-Bench (airline) | not reported | 58% ↗ | — | — |
| Tau2-Bench (retail) | not reported | 71.27% ↗ | — | — |
| Tau2-Bench (telecom) | not reported | 73.68% ↗ | — | — |
| TerminalBench | not reported | 39.51% ↗ | — | — |
| VitaBench | not reported | 24.3% ↗ | — | — |
| ZebraLogic | not reported | 89.3% ↗ | — | — |
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 V4 Pro minus LongCat Flash Chat 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 V4 Pro | LongCat Flash Chat | Edge |
|---|---|---|---|
| Context window | 1M tokens | 128K tokens | DeepSeek V4 Pro |
| Max output | 384K tokens | — | — |
| Input price / 1M | $0.435 ↗ | — | — |
| Output price / 1M | $0.87 ↗ | — | — |
| Cached input / 1M | $0.004 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.31 | — | — |
| Modalities | text | text | Tie |
| Released | 2026-08-13 | 2025-09-01 | — |
| Cited benchmark scores | 11 | 31 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
DeepSeek V4 Pro vs …
Models sharing the most benchmarksMore matchups
LongCat Flash Chat vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V4 Pro and LongCat Flash Chat on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.