MiMo-V2.6 Pro
Open weights that score level with Opus 5 on agents, for cents.
Reference benchmarks for MiMo-V2.6 Pro
These are external benchmarks I pulled from the source comparison guides on agentos.guide — SWE-bench Verified, DRACO, Kilo plan rubric, build-time measurements, vendor-reported coding scores. They are not goldiebench medal scores (those come only from same-prompt one-shot creative coding tasks in the matrix). I surface them here so the spec sheet for MiMo-V2.6 Pro is honest about what's measured.
What is MiMo-V2.6 Pro?
MiMo-V2.6 Pro is the Xiaomi frontier model with a 1,000,000 tokens context window, released 2026-09. Tagline: Open weights that score level with Opus 5 on agents, for cents.. Official source: mimo.xiaomi.com/mimo-v2-6.
Pricing detail. Xiaomi's September 2026 open-weight flagship (MIT licence, 1.02T total / 42B active parameters). $0.435 per million input tokens and $0.87 per million output on OpenRouter, with cache hits at a fraction of a cent, which is roughly a quarter of Grok 4.7 and a twentieth of the closed frontier models it scores level with on agent benchmarks.
How I use it inside the Agent OS. Benched on all 50 GoldieBench tasks through OpenRouter at the model's default reasoning effort: one-shot build, real rendered poster, Opus 4.8 vision judge, game tasks skill-infused. No retries, no hand fixes; the broken builds are scored as they shipped.
What I built with MiMo-V2.6 Pro
Every model on Goldie Bench gets the same fixed prompt set — one shot, single HTML file out — and I score the result 0–10 inside the Agent Operating System. Here's what MiMo-V2.6 Pro shipped on the bench: 50 one-shot demos across 1,000,000 tokens of context. Of those, 50 are scored against the field with my honest 0–10 from the source guides at agentos.guide.
Strengths
- Simulations and visual pieces are top-tier one-shots: the black hole lensing scored 9.0 and the matrix rain, lava lamp, ocean waves, web desktop, boids and galaxy all landed 8.6 or higher
- Strong flight and driving output when the build holds together: a polished 3D dogfight (8.6), a flight sim (8.4) and the synthwave outrun (8.4)
- Big, complete files: builds ran 30 to 70 KB with full HUDs, control hints and settings panels
- The weights are MIT and on Hugging Face, so the same model can run on your own hardware
Trade-offs
- 18 of 50 builds scored under 5: long game files shipped with garbled tokens (a stray 'martin' or 'martial' identifier breaks the whole script), uninitialised references and bad canvas values, so the HUD paints but the 3D scene stays black
- Two hard crashes: the RPG threw an engine fault on load and the solar system rendered nothing at all
- It reasons for a long time at default effort: builds took 5 to 60 minutes each through OpenRouter
Best for
- Simulations, shaders and visual scenes in one shot, at a fraction of frontier prices
- High-volume agent work where an open, MIT-licensed model matters
- Pair it with a self-fix loop for games: the failures are single broken tokens, not missing ideas
Every benchmark — MiMo-V2.6 Pro's full scorecard
All 50 scored tasks, best first — the judge's 0–10 on the same rubric as the whole field. Click any bar for that task's cross-model page, or open this scorecard in the interactive graphs. Full editorial breakdown with judge quotes and sourced outside research: the MiMo-V2.6 Pro deep dive →.
Every demo by MiMo-V2.6 Pro
50 live demos, sorted by category. Click any tile to play the actual one-shot result. Verdicts and 0–10 scores are pulled from the source guides where I posted them publicly.
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVECompare MiMo-V2.6 Pro against every other model
Every head-to-head featuring MiMo-V2.6 Pro. Verdicts shown for scored pairs.
See all 66 comparisons across every model →
Quick pill index
Direct comparisons against every other scored model on the bench:
MiMo-V2.6 Pro vs Fusion MiMo-V2.6 Pro vs Claude Opus 5 MiMo-V2.6 Pro vs Hermes MoA MiMo-V2.6 Pro vs GPT-5.6 Sol MiMo-V2.6 Pro vs Claude Fable 5 MiMo-V2.6 Pro vs Qwen 3.8 MiMo-V2.6 Pro vs Grok MiMo-V2.6 Pro vs MiniMax M3 MiMo-V2.6 Pro vs Fugu Ultra MiMo-V2.6 Pro vs Kimi K3 MiMo-V2.6 Pro vs GLM-5.2 MiMo-V2.6 Pro vs Fugu Mini MiMo-V2.6 Pro vs Muse Spark 1.2 MiMo-V2.6 Pro vs Opus 4.8 MiMo-V2.6 Pro vs Kimi K2.7 MiMo-V2.6 Pro vs Grok 4.7 MiMo-V2.6 Pro vs Qwable 5 27B Coder MiMo-V2.6 Pro vs Gemini 3.6 Flash MiMo-V2.6 Pro vs Claude Sonnet 5 MiMo-V2.6 Pro vs Qwen 3.7 MiMo-V2.6 Pro vs Fugu Ultra 1.1 MiMo-V2.6 Pro vs Inkling MiMo-V2.6 Pro vs Grok 4.6 MiMo-V2.6 Pro vs Agents-A1 MiMo-V2.6 Pro vs Gemma 4 12B · MLX MiMo-V2.6 Pro vs Laguna XS 2.1 MiMo-V2.6 Pro vs Qwythos 9B MiMo-V2.6 Pro vs LongCat-2.0 MiMo-V2.6 Pro vs Hy3 MiMo-V2.6 Pro vs Gemma-4 12B CoderRead more on agentos.guide: /xiaomi-mimo-v2-6
MiMo-V2.6 Pro — frequently asked
What is MiMo-V2.6 Pro?
MiMo-V2.6 Pro is Xiaomi's AI model — Open weights that score level with Opus 5 on agents, for cents. It has a 1M tokens context window and was released 2026-09.
How good is MiMo-V2.6 Pro at coding and one-shot builds?
On the GoldieBench one-shot build benchmark it averages 6.35/10 across 50 scored tasks, with 5 gold, 8 silver and 4 bronze medals.
How much does MiMo-V2.6 Pro cost?
$0.435 in / $0.87 out per M tokens. Xiaomi's September 2026 open-weight flagship (MIT licence, 1.02T total / 42B active parameters). $0.435 per million input tokens and $0.87 per million output on OpenRouter, with cache hits at a fraction of a cent, which
Where can I see MiMo-V2.6 Pro demos?
Every one-shot build is live and playable on this page and on the GoldieBench compare matrix — same prompt as every other model, no retries.
Run this stack yourself.
Every demo on this bench was built inside the Agent Operating System — one prompt, one shot, single HTML file out. The Agent OS, the prompts, the templates, the weekly walkthroughs and 4,000+ founders shipping with it every day all live inside the AI Profit Boardroom.