Claude Opus 4.8 vs DeepSeek V4 Pro
As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in 6 of 6 shared categories: General LLM, Reasoning, Science, Coding › Web dev, Long context, and Factuality.
Claude Opus 4.8
It used to be. Was SOTA in Coding › Web dev.
DeepSeek V4 Pro
#28 Best recorded rank: #28 in Science, as of Oct 14, 2026.
| Category | Claude Opus 4.8 | DeepSeek V4 Pro |
|---|---|---|
| General LLM | #20 · #20 in General LLM Margin 13.605442176870753 LMArena leaderboard dataset · Oct 13, 2026 | #44 · #44 in General LLM Margin 29.931972789115648 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #10 · #10 in Reasoning Margin 7.534246575342465 LMArena leaderboard dataset · Oct 13, 2026 | #45 · #45 in Reasoning Margin 31.506849315068493 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #27 · #27 in Science Margin — Epoch AI benchmarking hub · May 28, 2026 | #28 · #28 in Science Margin — Epoch AI benchmarking hub · Apr 24, 2026 |
| Coding | #12 · #12 in Coding Margin 59.09090909090909 Terminal-Bench Harbor Hub · Oct 6, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Apr 24, 2026 |
| Coding › Agentic | #12 · #12 in Coding › Agentic Margin 59.09090909090909 Terminal-Bench Harbor Hub · Oct 6, 2026 | — |
| Coding › Web dev | #33 · Was SOTA · Coding › Web dev Margin 29.90654205607477 LMArena leaderboard dataset · Oct 13, 2026 | #57 · #57 in Coding › Web dev Margin 52.33644859813084 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #10 · Was SOTA · Long context Margin 6.802721088435391 LMArena leaderboard dataset · Oct 13, 2026 | #43 · #43 in Long context Margin 29.25170068027211 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #13 · #13 in Vision Margin 36.842105263157904 Epoch AI benchmarking hub · May 28, 2026 | — |
| Factuality | #21 · #21 in Factuality Margin 16.417910447761187 LMArena leaderboard dataset · Oct 13, 2026 | #41 · #41 in Factuality Margin 31.343283582089555 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #12 · #12 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · May 28, 2026 | — |
Claude Opus 4.8: $10 per 1M blended tokens.
DeepSeek V4 Pro: $0.50895 per 1M blended tokens.
Claude Opus 4.8: closed weights.
DeepSeek V4 Pro: open weights.
General LLM: As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in General LLM at #20 against #44.
Reasoning: As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in Reasoning at #10 against #45.
Science: As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in Science at #27 against #28.
Coding › Web dev: As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in Coding › Web dev at #33 against #57.
Long context: As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in Long context at #10 against #43.
Factuality: As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in Factuality at #21 against #41.
Claude Opus 4.8 · DeepSeek V4 Pro
Claude Opus 4.8 or DeepSeek V4 Pro?
As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in 6 of 6 shared categories: General LLM, Reasoning, Science, Coding › Web dev, Long context, and Factuality.
Claude Opus 4.8 or DeepSeek V4 Pro for General LLM?
As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in General LLM at #20 against #44.
Claude Opus 4.8 or DeepSeek V4 Pro for Reasoning?
As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in Reasoning at #10 against #45.
Claude Opus 4.8 or DeepSeek V4 Pro for Science?
As of Oct 14, 2026, Claude Opus 4.8 leads DeepSeek V4 Pro in Science at #27 against #28.