Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Mimo V2.6 Flash

Xiaomi · 311B · open weights

Strongest in Cybersecurity (#1 of 9), weakest in Safety (#282 of 337). Above par in 11 of 16 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5 and Mimo V2.6 Pro and ahead of Gemini 3.6 Flash and Kimi K2.5.

§ 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.

Professional56.4#24/168
Cybersecurity59.7#1/9
Legal57.9#22/151
Finance56.5#30/151
Coding57#24/165
Agentic coding58.1#21/157
Human preference62.2#58/342
Human preference62.2#58/342
Reasoning51.8#77/178
Mathematics52.7#68/140
Safety45.5#282/337
Toxicity avoidance54#130/272
Secure code48.4#174/274
Harm refusal46.3#222/300
Jailbreak resistance34#240/272
Fairness42.6#252/300

§ 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.

Grok 3won 12 · lost 1
Mistral Large 3won 9 · lost 1
GPT-5.4 Miniwon 9 · lost 1
Grok Build 0.1won 8 · lost 2
GPT-5.4 Nanowon 8 · lost 2
Grok 4 Fastwon 8 · lost 2
Command Awon 12 · lost 3
DeepSeek V3won 12 · lost 3
DeepSeek R1won 12 · lost 3
Mistral Largewon 9 · lost 3
Mistral Smallwon 9 · lost 3
Gemini 2.0 Flashwon 11 · lost 4
Gemini 2.5 Flashwon 11 · lost 4
Grok 4won 11 · lost 4
Grok 4.1 Fastwon 11 · lost 4
Command R Pluswon 8 · lost 3
Gemma 4 31Bwon 10 · lost 4
Gemini 2.5 Flash Litewon 7 · lost 3
Qwen3.5 Flashwon 7 · lost 3
Gemini 3.1 Flash Litewon 7 · lost 3
Gemini 1.5 Prowon 9 · lost 4
GLM-4.5won 9 · lost 4
GPT-4.1 Nanowon 10 · lost 5
Claude 3.5 Haikuwon 10 · lost 5
GPT-4.1 Miniwon 10 · lost 5
Claude 3.7 Sonnetwon 10 · lost 5
Kimi K2won 10 · lost 5
DeepSeek V3.2won 10 · lost 5
GPT-6 Lunawon 10 · lost 5
Grok 4.3won 10 · lost 5
Gemini 2.5 Prowon 10 · lost 5
Kimi K2.6won 10 · lost 5
Jamba 1.6 Miniwon 7 · lost 4
Jamba 1.6 Largewon 7 · lost 4
Jamba 1.5 Miniwon 7 · lost 4
Jamba 1.5 Largewon 7 · lost 4
DeepSeek V4 Flashwon 10 · lost 6
Gemini 1.5 Flashwon 8 · lost 5
GPT OSS 20Bwon 8 · lost 5
Llama 4 Scout Instructwon 8 · lost 5
Gemma 2 9B Itwon 6 · lost 4
QwQ 32Bwon 6 · lost 4
Gemini 3.1 Prowon 6 · lost 4
GPT-4owon 9 · lost 6
GPT OSS 120Bwon 9 · lost 6
O3 Miniwon 9 · lost 6
Claude Sonnet 4won 9 · lost 6
O1won 9 · lost 6
Claude Haiku 4.5won 9 · lost 6
GLM-4.6won 9 · lost 6
Claude Opus 4won 9 · lost 6
MiniMax M3won 9 · lost 6
Inklingwon 9 · lost 6
Qwen3.7 Maxwon 9 · lost 6
GLM-5.2won 9 · lost 6
Ling 3.0 Flashwon 7 · lost 5
GPT-4o Miniwon 8 · lost 6
Claude 3.5 Sonnetwon 8 · lost 6
GPT-5 Miniwon 8 · lost 7
O4 Miniwon 8 · lost 7
GPT-4.1won 8 · lost 7
Kimi K2.5won 8 · lost 7
Gemini 3.6 Flashwon 8 · lost 7
GLM-5won 5 · lost 5
Gemini 3 Flashwon 5 · lost 5
GPT-4 Turbowon 6 · lost 6
O1 Miniwon 6 · lost 6
MiniMax M2.7won 7 · lost 8
Grok 4.7won 7 · lost 8
Mimo V2.5 Prowon 7 · lost 8
Gemini 3.5 Flashwon 7 · lost 8
Kimi K2 Thinkingwon 6 · lost 7
GPT-5 Nanowon 6 · lost 7
Gemini 3 Prowon 5 · lost 7
Kimi K2.7 Codewon 4 · lost 6
Gemma 2 27B Itwon 4 · lost 6
Qwen Maxwon 4 · lost 6
Gemma 3 27B Itwon 4 · lost 6
DeepSeek V4.1 Flashwon 4 · lost 6
O3won 6 · lost 9
Claude Sonnet 4.5won 6 · lost 9
GLM-5.1won 6 · lost 9
Grok 4.5won 6 · lost 9
Claude Sonnet 4.6won 5 · lost 8
GPT-6 Astrawon 4 · lost 7
GPT-5won 5 · lost 10
GPT-5.2won 5 · lost 10
GPT-5.6 Lunawon 5 · lost 10
GLM-5.3 Flashwon 5 · lost 10
Qwen3.8 Maxwon 5 · lost 10
Grok 4.6won 5 · lost 11
DeepSeek V4 Prowon 5 · lost 11
Gemini 3.8 Flashwon 5 · lost 11
Claude Opus 4.6won 4 · lost 9
Gemma 4 12Bwon 3 · lost 7
Claude Opus 4.5won 3 · lost 7
GLM-5.3won 3 · lost 7
GPT-5.1won 4 · lost 11
GPT-6 Solwon 4 · lost 11
Claude Sonnet 5won 4 · lost 11
GPT-5.4won 4 · lost 11
GPT-5.5won 4 · lost 11
Muse Spark 1.1won 4 · lost 11
Kimi K3won 2 · lost 8
GPT-5.6 Terrawon 3 · lost 12
GPT-5.6 Solwon 3 · lost 13
Claude Opus 4.7won 2 · lost 13
Muse Spark 1.3won 1 · lost 9
Claude Fable 5.1won 1 · lost 9
Claude Opus 4.8won 1 · lost 14
Claude Opus 5.5won 1 · lost 14
Mimo V2.6 Prowon 1 · lost 15
Claude Opus 5won 1 · lost 15

§ 3 · Sources

Where the numbers come from

3 publications, 14 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1454
Vals.ai ↗7 measuresread 2026-09-26
Vals · Legal Research Bench 37.98%Vals · Harvey Legal Agent Benchmark 11.25%Vals · Finance Agent 56.28%Vals · CyberBench 75.36%Vals · Vibe Code Bench 78.96% (OpenHands)Vals · Code Migration 40.93%Vals · ProofBench 63%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26
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

PublicAI Index badge for Mimo V2.6 Flash[![PublicAI Index](https://publicai.io/model-index/badge?model=mimo-v2-6-flash)](https://publicai.io/model-index/m/mimo-v2-6-flash)