DeepSeek V2.5 — Benchmarks

Benchmark scores for DeepSeek V2.5 aggregated from public leaderboards (3 boards), with how it ranks among open models and how it compares with its nearest neighbours. See hardware requirements for what you need to run it.

No llmrun Composite Score for DeepSeek V2.5: the score is only published for a model measured on at least 4 of the boards in the score panel, spanning at least 2 benchmark categories and including a reasoning or coding board — or on 3 boards that narrow its score to a 90% range of at most 15.6 points. Either way the results must come from at least two different benchmarks. Its individual scores below stand on their own — see how the llmrun Composite Score gets calculated.

DeepSeek V2.5 coding benchmarks

Writing, editing, and fixing real code — measured by whether the resulting program actually runs and passes tests.

Aider Polyglot
The Aider Polyglot benchmark measures real-world coding across several programming languages: the model edits code to solve Exercism exercises, and is scored on whether the final solution actually runs and passes the tests.
17.8%
17.8%
median 45.1%open leader 74.2%
Overall best: GPT 5 (Aug 07, 2025, high) 88.0%
29th percentile · #13 of 18 open · #60 of 69 all
#13 of 18
#60 of 69
Independent
Epoch AI · Sep 2024

DeepSeek V2.5 knowledge benchmarks

Breadth and depth of factual knowledge across many subjects, paired with the reasoning to apply it.

MMLU-Pro
MMLU-Pro is a harder, cleaned-up successor to MMLU with ten answer choices and more reasoning-heavy questions across 14 subjects, measuring broad knowledge and reasoning together.
65.8%
65.8%
median 52.0%open leader 88.0%
Overall best: Gemini-3.1-Pro 91.2%
69th percentile · #46 of 146 open · #116 of 257 all
#46 of 146
#116 of 257
Independent
TIGER-Lab

DeepSeek V2.5 instruction following benchmarks

How precisely a model obeys explicit, verifiable instructions — format, length, and content constraints — and, more broadly, how much people prefer its responses head-to-head in blind human voting.

LMArena Text
Arena (arena.ai, formerly LMArena / Chatbot Arena) ranks models by millions of blind, head-to-head human votes on real prompts. The Arena Score shown here is a Bradley-Terry rating computed with Arena's default style control, so higher means people preferred that model's answers more often — it's a relative rating, not a percentage, so compare it only to other models on this board.
1307.2
1307.2
median 1321.4open leader 1488.2
Overall best: Gemini 4 Carbon (High) 1527.5
46th percentile · #102 of 188 open · #270 of 408 all
#102 of 188
#270 of 408
Arena
Arena · Oct 2026

Scores aggregated from public benchmark sources (Epoch AI: 1 board, Arena: 1 board, TIGER-Lab: 1 board) — each linked from the benchmark pages. llmrun does not run these benchmarks. Percentiles and ranks are among open models in the llmrun catalogue; the median and leader marks refer to the same field.