MDL
MiMo-V2.5
Xiaomi
Verified against Artificial Analysis · Jul 13, 2026
Capability
85
percentile index
Price /M
$0.14 / $0.28
in / out
Context
1M
tokens
Avg score
59.3
7 benchmarks
AA Intelligence
37.2
index
Speed
85 tok/s
TTFT 2s
Released
Apr 22, 2026
About
MiMo-V2.5 is a proprietary model in the MiMo family from Xiaomi. Benchmarked on 7 evals, averaging 59.3.
Benchmark scores · 7
avg 59.3 — higher is betterThe research behind this model
all papers mentioning it →Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning BenchmarksMay 22, 2026Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBenchMay 16, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed85 tok/s
Latency (TTFT)2s
First answer25s
Price in / out$0.14 / $0.28 per 1M
Blended price$0.175 / 1M
Coding index56.8
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.28/M