MiMo-V2.6-Pro Benchmarks, Specifications & Availability

Explore MiMo-V2.6-Pro from Xiaomi: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.

Compare MiMo-V2.6-Pro with other models →Explore data coverage

Published specifications

Provider: Xiaomi
Access: Open weights
License: MIT
Context window: 1M
Total parameters: 1.02T
Active parameters: 42B
Released: 2026-09-21
Modalities: text, image, video, audio
Family: MiMo-V2.6

Model card · Announcement · Website · OpenRouter

Model notes

Sparse MoE; open weights + RL environments/training code announced. Open weights verified on Hugging Face https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL (2026-09-25).

Pricing · OpenRouter

Dated cached OpenRouter rates in USD per 1M tokens. Open the dashboard for live enhancements. Per-metric endpoint minima can refer to different providers; they are not a guaranteed combined rate from one endpoint.

Recorded pricing tiers
Tier	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M	Date & source
Default	[object Object]	[object Object]	[object Object]	—	2026-10-03 · OpenRouter source

Recorded pricing notes

min-healthy endpoint minima 2026-10-01; discount flag 0.05 on GMICloud (undocumented, not applied); discount flag 0.05 on GMICloud (undocumented, not applied); min-healthy endpoint minima 2026-10-01; discount flag 0.05 on GMICloud (undocumented, not applied); discount flag 0.05 on GMICloud (undocumented, not applied); min-healthy endpoint minima 2026-10-02; discount flag 0.05 on GMICloud (undocumented, not applied); discount flag 0.05 on GMICloud (undocumented, not applied); min-healthy endpoint minima 2026-10-03

Official / vendor benchmarks

Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.

Official / vendor headline scores; expand evidence for every record
Benchmark / evaluator	Headline score	Evidence
Agents' Last Exam	31.6%unknown effort	All 1 recorded result & sources 31.6% · raw 31.6 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
AutomationBench v1.0.6	53.1%unknown effort	All 1 recorded result & sources 53.1% · raw 53.1 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
CyberGym	94%unknown effort	All 1 recorded result & sources 94% · raw 94 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
DeepSWE v1.1	71.9%unknown effort	All 1 recorded result & sources 71.9% · raw 71.9 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
ExploitBench	47.9%unknown effort	All 1 recorded result & sources 47.9% · raw 47.9 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
ExploitGym	17.8%unknown effort	All 1 recorded result & sources 17.8% · raw 17.8 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
GDPval-AA 2.1	1673unknown effort	All 1 recorded result & sources 1673 · raw 1673 Elo Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
JobBench	62%unknown effort	All 1 recorded result & sources 62% · raw 62 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
MiMo Code Bench	63.2%unknown effort	All 1 recorded result & sources 63.2% · raw 63.2 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
MiMo Cyber Bench	80.2%unknown effort	All 1 recorded result & sources 80.2% · raw 80.2 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
MiMo VisualCoding	72.3%unknown effort	All 1 recorded result & sources 72.3% · raw 72.3 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
OSWorld-Verified	82%unknown effort	All 1 recorded result & sources 82% · raw 82 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
ProgramBench	26.5%unknown effort	All 1 recorded result & sources 26.5% · raw 26.5 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 From Xiaomi HF evaluation table https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
SEC-Bench Pro	66.3%unknown effort	All 1 recorded result & sources 66.3% · raw 66.3 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
Terminal-Bench 2.1	89.9%unknown effort	All 1 recorded result & sources 89.9% · raw 89.9 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
Terminal-Bench 4.0	34.9%unknown effort	All 1 recorded result & sources 34.9% · raw 34.9 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
Toolathlon-Verified	76.9%unknown effort	All 1 recorded result & sources 76.9% · raw 76.9 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL

Independent evaluators

Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.

Independent evaluator headline scores; expand evidence for every record
Benchmark / evaluator	Headline score	Evidence
Intelligence Index · Artificial Analysis	46unknown effort	All 1 recorded result & sources 46 · raw 46 index Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/mimo-v2-6-pro
Cost per Intelligence Index task · Artificial Analysis	$0.13unknown effort	All 1 recorded result & sources $0.13 · raw 0.13 USD Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/mimo-v2-6-pro
Output speed · Artificial Analysis	46 tok/sunknown effort	All 1 recorded result & sources 46 tok/s · raw 46 tok/s Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/mimo-v2-6-pro
Vals Index · Vals AI	55.2%unknown effort	All 1 recorded result & sources 55.2% · raw 55.2 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Refreshed from current Vals leaderboard. Cost/test $0.41. https://www.vals.ai/benchmarks/vals_index
Bugs fixed /105 · Bug Hunt Bench	22.7 fixesunknown effort	All 1 recorded result & sources 22.7 fixes · raw 22.7 fixes Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Harness: Claude Code / OpenRouter; effort default; 3 runs; evaluation 2026-09-22. Best documented score for this effort in Oct 1 README. Headline: best documented model run. https://github.com/phuryn/bug-hunt-bench
GDPval-AA Elo · Artificial Analysis	1673unknown effort	All 1 recorded result & sources 1673 · raw 1673 Elo Headline · unknown effort · Independent evaluator Source/record date: 2026-09-23 GDPval-AA v2.1 Elo; MiMo-V2.6-Pro https://artificialanalysis.ai/evaluations/gdpval-aa
Vibe Code Bench v1.1 · Vals AI	85.2%unknown effort	All 1 recorded result & sources 85.2% · raw 85.22 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Refreshed from current Vals leaderboard. Harness: OpenHands. Cost/test $1.04. https://www.vals.ai/benchmarks/vibe-code

Read how we select and source scores or the comparison guide.