Deepseek Llm 67B Chat — Benchmarks

Benchmark scores for Deepseek Llm 67B Chat aggregated from public leaderboards (4 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 Llm 67B Chat: 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 Llm 67B Chat reasoning benchmarks

Multi-step logic and problem-solving — can the model think through a hard problem rather than recall an answer.

GPQA Diamond
GPQA Diamond is a set of extremely hard, graduate-level science questions (physics, chemistry, biology) written by domain experts and filtered so that skilled non-experts with web access still fail. It measures genuine reasoning rather than memorization.
24.6%
24.6%
median 54.0%open leader 93.1%
Overall best: Gemini 4 Argon (high) 96.4%
8th percentile · #90 of 98 open · #291 of 300 all
#90 of 98
#291 of 300
Independent
Epoch AI · Nov 2023

Deepseek Llm 67B Chat math benchmarks

Symbolic and quantitative problem-solving, from competition math to multi-step calculation.

AIME 2024/2025
AIME (American Invitational Mathematics Examination) is a prestigious high-school competition of hard, integer-answer problems. It's a widely-cited yardstick for multi-step mathematical reasoning, here on the 2024–2025 papers.
0.8%
0.8%
median 52.8%open leader 98.6%
Overall best: Claude Fable 5 (high) 100.0%
6th percentile · #80 of 86 open · #276 of 283 all
#80 of 86
#276 of 283
Independent
Epoch AI · Nov 2023
MATH Level 5
MATH Level 5 covers the hardest tier of competition-mathematics problems, testing multi-step symbolic and quantitative reasoning.
6.4%
6.4%
median 41.6%open leader 96.6%
Overall best: GPT 5 (Aug 07, 2025, high) 98.1%
11th percentile · #35 of 39 open · #102 of 107 all
#35 of 39
#102 of 107
Independent
Epoch AI · Nov 2023

Deepseek Llm 67B Chat 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.
1185.1
1185.1
median 1321.5open leader 1487.1
Overall best: Gemini 4 Argon (High) 1523.9
20th percentile · #150 of 187 open · #343 of 405 all
#150 of 187
#343 of 405
Arena
Arena · Oct 2026

Scores aggregated from public benchmark sources (Epoch AI: 3 boards, Arena: 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.