MiniMax M2.1 — Benchmarks

Benchmark scores for MiniMax M2.1 aggregated from public leaderboards (5 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 →

106.2

90% range 99.5–112.9 · from 3 boards

CodingNot enough data yet
AgentsNot enough data yet
MathNot enough data yet
ScienceNot enough data yet
ReasoningNot enough data yet

MiniMax M2.1 coding benchmarks

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

Terminal-Bench
Terminal-Bench measures whether a model can complete real, end-to-end tasks in a command-line environment — running commands, editing files, and chaining steps — making it an agentic test of practical software skill.
36.6%
36.6%
median 31.7%open leader 52.4%
Overall best: GPT 5.5 (unspecified) 84.7%
67th percentile · #6 of 16 open · #36 of 57 all
#6 of 16
#36 of 57
Lab-reported
Epoch AI · Dec 2025
ALE-Bench
ALE-Bench, from Sakana AI and AtCoder, tests long-horizon algorithmic optimisation using problems drawn from AtCoder Heuristic Contests, where there is no single correct answer and solutions are scored on quality. Results are reported as an AtCoder-style performance rating, where higher is better.
623.8
623.8
median 694.1open leader 1524.5
Overall best: GPT 6 Astra Max 2951.3
43rd percentile · #25 of 43 open · #91 of 122 all
#25 of 43
#91 of 122
Lab-reported
Epoch AI · Dec 2025

Other results (1)· leaderboard-only, not part of the llmrun Score

LMArena WebDev
Code Arena (formerly WebDev Arena) is Arena's head-to-head coding leaderboard: two models each build a real web app or UI from the same prompt, and people vote blind on which result is better. The rating shown is a relative Bradley-Terry score, not a percentage — compare it only to other models on this board.
1384.3
1384.3
median 1411.4open leader 1655.2
Overall best: Claude Opus 5.5 (Max) 1807.3
41st percentile · #31 of 52 open · #99 of 138 all
#31 of 52
#99 of 138
Arena
Arena · Oct 2026

MiniMax M2.1 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.
88.0%
88.0%
median 52.1%open leader
Overall best: Gemini-3.1-Pro 91.2%
top · #1 of 145 open · #6 of 257 all
#1 of 145
#6 of 257
Independent
TIGER-Lab

MiniMax M2.1 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.
1384.4
1384.4
median 1321.5open leader 1487.1
Overall best: Gemini 4 Argon (High) 1523.9
69th percentile · #59 of 187 open · #177 of 405 all
#59 of 187
#177 of 405
Arena
Arena · Oct 2026

Score vs VRAM in the ≤192 GB tier

MiniMax M2.1
Other models
Best Score for its VRAM
x: VRAM (GB, log scale) · y: llmrun Score

#21 of 78 that fit ≤192 GB

Each dot is a model at the best quant that fits ≤192 GB. 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 ≤192 GB ranking →

MiniMax M2.1 vs its neighbours

Same boards for the nearest open models per llmrun Score. The highest score in each row is marked.

Board	MiniMax M2.1this model	Qwen3.8 27Bbest in classQ4_K_M · 18 GB	MiMo V2.5nearest by ScoreQ4_K_M · 188 GB	Qwen3 235B A22B Thinking 2507nearest by ScoreQ4_K_M · 143 GB	MiniMax M2.7nearest by ScoreQ4_K_M · 140 GB
llmrun Score	106.2	122.1	108.3	108.2	107.4
Terminal-Bench	36.6%	—	—	—	45.1%
ALE-Bench	623.8	—	514.0	—	599.3
MMLU-Pro	88.0%	—	—	84.5%	—
LMArena Text	1384.4	1437.8	1433.8	1399.8	1415.0
Compare head to head		Compare	Compare	Compare	Compare

Scores aggregated from public benchmark sources (Epoch AI: 2 boards, Arena: 2 boards, 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.