Mixtral 8x7B Instruct v0.1 — Benchmarks

Benchmark scores for Mixtral 8x7B Instruct v0.1 aggregated from public leaderboards (6 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.

llmrun Composite Score →

65.1

90% range 58.0–72.2 · from 4 boards

CodingNot enough data yet
AgentsNot enough data yet
MathNot enough data yet
ScienceNot enough data yet
Reasoning68.790% range 55–82

Mixtral 8x7B Instruct v0.1 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.
30.6%
30.6%
median 54.0%open leader 93.1%
Overall best: Gemini 4 Argon (high) 96.4%
18th percentile · #81 of 98 open · #278 of 300 all
#81 of 98
#278 of 300
Independent
Epoch AI · Dec 2023
DTBench
DTBench is a set of handcrafted, expert-validated multiple-choice questions on decision theory — Newcomb-like problems and related puzzles — built by the Conceptual Reasoning Index project with Anthropic. It tests whether a model can follow an abstract argument rather than recall a fact.
49.6%
49.6%
median 67.7%open leader 93.9%
Overall best: Claude Opus 5.5 Max 98.9%
12th percentile · #60 of 68 open · #200 of 214 all
#60 of 68
#200 of 214
Lab-reported
Epoch AI · Dec 2023
ForecastBench
ForecastBench, from the Forecasting Research Institute, asks models to predict real-world future events, with questions that only resolve after the model's training cutoff so the answers can't have been memorised. It is scored as a difficulty-adjusted Brier index, where higher is better.
56.3
56.3
median 58.1open leader 61.9
Overall best: O3 (Apr 16, 2025, unspecified) 62.5
14th percentile · #23 of 26 open · #74 of 82 all
#23 of 26
#74 of 82
Lab-reported
Epoch AI · Dec 2023

Mixtral 8x7B Instruct v0.1 math benchmarks

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

MATH Level 5
MATH Level 5 covers the hardest tier of competition-mathematics problems, testing multi-step symbolic and quantitative reasoning.
10.0%
10.0%
median 41.6%open leader 96.6%
Overall best: GPT 5 (Aug 07, 2025, high) 98.1%
13th percentile · #34 of 39 open · #101 of 107 all
#34 of 39
#101 of 107
Independent
Epoch AI · Dec 2023

Mixtral 8x7B Instruct v0.1 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.
43.3%
43.3%
median 52.1%open leader 88.0%
Overall best: Gemini-3.1-Pro 91.2%
36th percentile · #93 of 145 open · #187 of 257 all
#93 of 145
#187 of 257
Independent
TIGER-Lab

Mixtral 8x7B Instruct v0.1 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.
1197.3
1197.3
median 1321.5open leader 1487.1
Overall best: Gemini 4 Argon (High) 1523.9
22nd percentile · #147 of 187 open · #339 of 405 all
#147 of 187
#339 of 405
Arena
Arena · Oct 2026

Score vs VRAM in the 24 GB tier

Mixtral 8x7B Instruct v0.1
Other models
Best Score for its VRAM
x: VRAM (GB) · y: llmrun Score

#31 of 35 that fit 24 GB

Each dot is a model at the best quant that fits a 24 GB GPU. The line joins the models with the best Score for their VRAM; a dot below it is beaten by a model that needs no more memory.

Full 24 GB ranking →

Mixtral 8x7B Instruct v0.1 vs its neighbours

Same boards for the nearest open models per llmrun Score and the best model that fits 24 GB. The highest score in each row is marked.

Board	Mixtral 8x7B Instruct v0.1this model	Qwen3.8 27Bbest in classQ4_K_M · 18 GB	Gemma 3 27B ITnearest by ScoreQ4_K_M · 22 GB	Mistral Small 3.1 24B Instruct 2503nearest by ScoreQ4_K_M · 18 GB	Gemma 2 27B ITnearest by ScoreQ4_K_M · 20 GB
llmrun Score	65.1	122.1	79.4	79.0	72.7
GPQA Diamond	30.6%	—	47.7%	47.5%	36.5%
DTBench	49.6%	88.0%	52.5%	58.6%	—
MATH Level 5	10.0%	—	74.0%	46.8%	27.9%
MMLU-Pro	43.3%	—	67.5%	—	56.5%
LMArena Text	1197.3	1437.8	1365.5	1302.7	1289.5
Compare head to head		Compare	Compare	Compare	Compare

Scores aggregated from public benchmark sources (Epoch AI: 4 boards, 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.