Scaling Reinforcement Learning Toward Self-Improvement
MiMo-V2.6-Flash-RL is the efficiency-balanced checkpoint of the MiMo-V2.6 series. The series is built to scale reinforcement learning toward self-improvement — scaling RL compute, environment diversity, and grader compute together, so the model keeps expanding its capability frontier through exploration and feedback. Key features include:
Figure 1. MiMo-V2.6 architecture.
| Model | Download |
|---|---|
| MiMo-V2.6-Pro-RL | 🤗 HuggingFace · 🤖 ModelScope |
| MiMo-V2.6-Flash-RL | 🤗 HuggingFace · 🤖 ModelScope |
| 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 |
| Component | MiMo-V2.6-Flash-RL |
|---|---|
| Layers (Total / SWA / GA) | 48 / 39 / 9 |
| Hidden Size | 4096 |
| SWA Heads (Q/KV) | 64 / 8 |
| GA Heads (Q/KV) | 64 / 4 |
| Head Dimensions (QK / V) | 192 / 128 |
| Sliding Window Size | 128 |
| Routed Experts (Total / Activated) | 256 / 8 |
| Max Context Length | 1M |
| MTP / Speculative Decoder | 5 SWA layers, window 1024 |
The first Transformer block uses global attention with a dense FFN. Remaining blocks interleave local SWA and GA; both use sparse MoE FFNs without shared experts.
| Configuration | Value |
|---|---|
| Layers (Total / SWA / GA) | 28 / 24 / 4 |
| Hidden Size | 1280 |
| Attention Heads (Q / KV) | 32 / 8 |
| Head Dimension | 64 |
| Patch Size (T × H × W) | 2 × 16 × 16 |
| Sliding Window (Left / Right) | 64 / 64 |
| Spatial Merge Size | 2 × 2 |
| Parameters | 681M |
AudioTokenizer encoder: 24 layers (12 SWA / 12 GA), hidden 1024, 20 RVQ codebooks, 308M parameters. Audio patch encoder: 6 layers, 127M parameters; four frames per patch (25 Hz → 6.25 Hz).
5-layer SWA MTP drafter (DFlash-style). Predicts 7 subsequent tokens per forward pass for parallel verification.
For best performance, follow the SGLang MiMo cookbook. Docker image: lmsysorg/sglang:latest.
sglang serve \
--trust-remote-code \
--model-path XiaomiMiMo/MiMo-V2.6-Flash-RL \
--tp 8 \
--dp 2 \
--enable-dp-attention \
--enable-dp-lm-head \
--mm-enable-dp-encoder \
--mem-fraction-static 0.65 \
--chunked-prefill-size 16384 \
--speculative-algorithm EAGLE \
--speculative-num-steps 3 \
--speculative-eagle-topk 1 \
--speculative-num-draft-tokens 4 \
--enable-multi-layer-eagle \
--reasoning-parser mimo \
--tool-call-parser mimo \
--host 0.0.0.0 \
--port 30000
Follow the vLLM MiMo-V2.5 recipe. Stable vLLM may lag; pre-built image: docker pull vllm/vllm-openai:mimov25-cu129.
vllm serve XiaomiMiMo/MiMo-V2.6-Flash-RL \
--tensor-parallel-size 4 \
--trust-remote-code \
--gpu-memory-utilization 0.95 \
--max-model-len auto \
--reasoning-parser mimo \
--tool-call-parser mimo \
--enable-auto-tool-choice \
--generation-config vllm
Recommended sampling: temperature=1.0, top_p=0.95.
Also available in AI Studio, MiMo Code, Xiaomi MiMo Desktop, Xiaomi MiMo Open Platform API, and OpenRouter.
@misc{mimo2026v26flash,
title={MiMo-V2.6-Flash-RL},
author={{Xiaomi MiMo Team}},
year={2026},
howpublished={\url{https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL}},
}
For questions or feedback, reach us at mimo@xiaomi.com or join our community:
You are solely responsible for your use of XiaomiMiMo/MiMo-V2.6-Flash-RL and any outputs, actions, or consequences arising therefrom, and you agree not to use the XiaomiMiMo/MiMo-V2.6-Flash-RL or any derivatives thereof:
This notice is an informational reminder only and does not amend the applicable model licence or impose additional licence conditions. The permissions granted under that licence remain unaffected. Nothing in this notice restricts uses permitted by applicable law, including applicable exceptions and limitations.
mimo-legal@xiaomi.com. For information on submitting a complaint, please visit the https://mimo.xiaomi.com.