Ollama · mimo-v2.6-flash

## MiMo-V2.6-Flash-RL: Scaling Reinforcement Learning Toward Self-Improvement **MiMo-V2.6-Flash-RL** is the efficiency-balanced checkpoint of Xiaomi's MiMo-V2.6 series. It is a sparse Mixture-of-Expe…

ollama/mimo-v2.6-flash

## MiMo-V2.6-Flash-RL: Scaling Reinforcement Learning Toward Self-Improvement

**MiMo-V2.6-Flash-RL** is the efficiency-balanced checkpoint of Xiaomi's MiMo-V2.6 series. It is a sparse Mixture-of-Experts model with 309B total parameters and 15B active per token. Text, images, video, and audio go through one model, and a 1M token context covers long repositories, tool traces, and multi-session agent runs.

**One RL run.** Coding, general agents, visual tasks, and cybersecurity train together in a single mixed reinforcement learning run instead of separate per-domain runs. Fully asynchronous Group Relative Policy Optimization (GRPO) runs on large batches: 1,568 prompts with 16 rollouts per step. Mixing tasks and harnesses in the same batch lets capabilities reinforce each other and transfer to harnesses the model never saw in training.

**Scaling the reward signal.** Pass/fail grading cannot rank two solutions that both pass. Groupwise Reward Synthesis (GRS) builds task-specific rubrics offline from contrasting rollouts and combines rubric quality with test outcomes. Groupwise Advantage Redistribution (GAR) ranks passing trajectories online and moves advantage toward higher-quality solutions, which steers the model toward shorter paths and fewer tokens per task.

**Architecture.** The backbone has 48 Transformer layers, 39 with sliding-window attention and 9 with global attention, over 256 routed experts with 8 active per token. Vision runs through a 681M parameter MiMo ViT. Audio uses a 308M AudioTokenizer and a 127M audio patch encoder. A 5-layer speculative decoder predicts 7 tokens per forward pass for parallel verification. After mixed RL, Multi-Prefix Multi-Teacher On-Policy Distillation (MOPD2) extends capabilities to hard-to-verify tasks.

| Benchmark | MiMo-V2.6 Pro | MiMo-V2.6 Flash | MiMo-V2.5 Pro | Claude Opus 5 | GPT-5.6 Sol | Claude Fable 5 | | :--- | :---: | :---: | :---: | :---: | :---: | :---: | | **Code Agent** | | | | | | | | DeepSWE v1.1 | 71.9 | 67.9 | 19.0 | 74.0 | 73.0 | 70.0 | | ProgramBench | 26.5 | 26.0 | 12.5 | 37.0 | 25.0 | 33.0 | | MiMo Code Bench | 63.2 | 61.2 | 40.4 | 68.6 | 59.3 | - | | **General Agent** | | | | | | | | AutomationBench v1.0.6 | 53.1 | 52.3 | 16.0 | 50.3 | 45.8 | 46.2 | | Toolathlon-Verified | 76.9 | 73.6 | 49.1 | 80.6 | 74.9 | 77.9 | | GDPval-AA 2.1 | 1673 | - | 1107 | 1708 | 1588 | 1595 | | Agents' Last Exam | 31.6 | 27.6 | 13.2 | 31.6 | 30.8 | 25.7 | | Terminal Bench 4.0 | 34.9 | 28.8 | 1.5 | 49.0 | 39.9 | 42.4 | | Terminal Bench 2.1 | 89.9 | 87.6 | 65.2 | 89.1 | 88.8 | 84.3 | | OSWorld-Verified | 82.0 | 80.8 | - | 83.4 | 83.0 | 86.0 | | JobBench | 62.0 | 61.2 | 25.0 | 65.7 | 45.4 | 57.4 | | **Cybersecurity** | | | | | | | | CyberGym | 94.0 | 95.1 | 40.0 | - | - | - | | MiMo Cyber Bench | 80.2 | 77.2 | 0.0 | - | - | - | | ExploitGym | 17.8 | 6.0 | 0.2 | 22.1 | 30.3 | 28.4 | | ExploitBench | 47.9 | 25.3 | 16.6 | 70.0 | 78.5 | 78.0 | | SEC Bench Pro | 66.3 | 47.5 | 17.7 | - | 79.1 | - | | **Visual Agent** | | | | | | | | MiMo VisualCoding | 72.3 | 71.5 | - | 70.0 | 73.4 | 69.1 |

### Reference

[MiMo-V2.6 Technical Report](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL/blob/main/MiMo_V2_6_technical_report.pdf)

Specifications & capabilities

Published model ID
mimo-v2.6-flash

Deployments & artifacts

1–2 / 2

ollama

source id
ollama
execution mode
cloud
parameter size
309000000000
parameter count
309000000000
parameter count is approximate
false
quantization level
FP8
context window
1048576
context window is approximate
false
artifact size bytes
168268709272
architecture
mimo_v2
thinking
values
  • false
  • true
default
true
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
cloud
parameter size
309B
parameter count
309000000000
parameter count is approximate
false
quantization level
FP8
context window
1048576
context window is approximate
false
architecture
mimo_v2
thinking
values
  • false
  • true
default
true
updated at
2026-11-16T08:10:06.079865+00:00
metadata warning
Registry digest differs from the catalog hint. Both observations are retained; representation or tag revision may differ.

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace