‹ PublicAI Index
The LLM benchmark aggregator.
MiMo V2.6 Flash
Xiaomi · 311B · open weights
Strongest in Cybersecurity (#7 of 47), weakest in Safety (#276 of 329). Above par in 16 of 23 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 4 Argon and Claude Fable 5 and ahead of Qwen3 235B A22B Instruct and GPT-4.1.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Agents59−7.4#20/2982/6
Knowledge work64.4−6.3#25/2082/2
Coding55.2−11#33/1791/6
Agentic coding55.6−11.3#33/1731/5
Human preference61.3−7.5#68/3541/1
Human preference61.3−7.5#68/3541/1
Professional52.2−10.2#70/1941/2
Cybersecurity59.4−4.5#7/471/1
Biology research49.5−21.2#18/311/1
IT operations42.3−31.5#19/331/1
Finance55.5−6.9#42/1621/1
Legal52.6−13.3#72/1731/1
Medical52.3−14.2#74/1491/1
Reasoning50.7−14.7#93/1951/5
Mathematics51.1−12.7#79/1521/2
Core abilities50.2−15.1#95/1991/4
General intelligence50.3−19.1#83/1781/3
Safety45.5−15.9#276/3291/3
Toxicity avoidance53.9−5.1#129/2681/1
Secure code48.2−18#174/2701/1
Harm refusal46.2−15.3#219/2921/2
Jailbreak resistance33.9−31.1#236/2681/1
Fairness42.5−27.5#244/2921/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for MiMo V2.6 Flash, left for the other.
§ 3 · Sources
Where the numbers come from
6 publications, 21 figures. Every one links to the page it was read from.
LMArena Text 1448
Artificial Analysis Intelligence Index 27
GDPval-AA 1614
AA-Briefcase 1487
Vals · Legal Research Bench 37.98%Vals · Harvey Legal Agent Benchmark 13.33%Vals · Finance Agent 56.28%Vals · MedCode 41.06%Vals · MedScribe 85.28%Vals · BioMysteryBench 69.26%Vals · CyberBench 75.36%Vals · SRE Bench 4.2%Vals · Vibe Code Bench 78.96% (OpenHands)Vals · Code Migration 40.93%Vals · ProofBench 63%
Enkrypt · Jailbreak risk 26.3%Enkrypt · Harmful content risk 2.2%Enkrypt · CBRN risk 51.7%Enkrypt · Toxicity risk 3.5%Enkrypt · Bias risk 89.4%Enkrypt · Insecure code risk 36.9%
Badge
[](https://publicai.io/model-index/m/mimo-v2-6-flash)