Models · Xiaomi MiMo · Out sinceReleased 21 Sep 2026
MiMo-V2.6-Flash
MiMo-V2.6-Flash is made by Xiaomi MiMo. We don't have enough test results yet to rank it. It's cheap to use. Its makers have published it, so you can run it on your own servers.
Auto-created from OpenRouter catalog; verify details.
- —
- —
- —
- Cheap$0.14 / $0.28
- $0.18
- 1.1M
- —
- 18 (18 independent18 indep.)
- 21 Sep 2026
- Xiaomi MiMo
- —
Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.
You can't choose how long this one thinks.
No adjustable reasoning setting listed.
OpenRouter is a service that gives access to many AI models in one place. This model is listed there as xiaomi/mimo-v2.6-flash.
Route it as xiaomi/mimo-v2.6-flash at $0.14 in / $0.28 out per 1M tokens, 1.1M context. Listed since 21 Sep 2026.
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Run it yourself
Self-hosting
On your own servers,Licence, sizeunder your own control.and hardware.
- Yes
- 309B / 15B
- No
Needs one full AI server.
≤ 1.1 TB at 8-bit (one 8×H200 node). Weights ≈ 324 GB at 8-bit, 170 GB at 4-bit (+10–30% for KV cache). MoE: 15B active per token.
Languages: Languages: HF metadata: en, zh.
Training it further: Fine-tuning: No fine-tuning recipe in card.
Quantisations: mixed fp8/4-bit packed weights as released, gguf (community: ggml-org/MiMo-V2.6-Flash-RL-GGUF). Engines: SGLang, vLLM.
Download (Hugging Face)Weights on Hugging Face ↗huggingface.co ↗huggingface.co ↗
Every test result
Every result
All the numbers,with where they came from.
Every result we've found for this model, with who measured it and a link to where we read it.
All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.
| NotesNotes | ||||||
|---|---|---|---|---|---|---|
| AA-LCR | 74.3% | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-LCR accuracy, AA-run (long multi-document reasoning) |
| AA-Omniscience Accuracy | 27.0% | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | |
| AA-Omniscience Hallucination Rate | 54.4% | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | share of non-correct answers that were wrong instead of abstaining; = 1 - AA 'omniscienceNonHallucination' field (equals breakdown.hallucinationRate on the eval page) |
| AA-Omniscience Index | -12.7 | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-Omniscience Index (-100..100): correct minus incorrect, abstentions not penalised |
| Artificial Analysis Intelligence Index | 37.9 | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug mimo-v2-6-flash; list price $0.14/0.28 per 1M in/out; cost to run AA Intelligence Index $0.06/task |
| Artificial Analysis output speed | 51 tok/s | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | tokens/sec (median output speed, first-party API); TTFT 3.9s; list price $0.14/0.28 per 1M in/out |
| Humanity's Last Exam | 35.1% | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-run evaluation (AA slug mimo-v2-6-flash) |
| IOI (Vals) | 47.7% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | — | ±4.785 stderr; $0.215/test |
| LMArena Text - Expert | 1514 | Defaultmimo-v2.6-flash | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 20 (rank range 3-70); 95% CI 1490.7-1537.9; 609 votes; style-controlled |
| ProgramBench (fully resolved) | 0.5% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | mini-SWE-agent | ±0.5 stderr; $0.471/test; strict fully-resolved rate |
| SciCode | 51.3% | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-run evaluation (AA slug mimo-v2-6-flash) |
| Terminal-Bench 2.1 | 76.4% | Default | Independent testIndependentVals.ai ↗ | 27 Sep 2026 | Terminus 2 | ±1.716 stderr; $0.023/test |
| Terminal-Bench 4.0 | 24.2% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | mini-SWE-agent | ±1.515 stderr; $0.216/test |
| Terminal-Bench 4.0 | 22.7% | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-run evaluation (AA slug mimo-v2-6-flash) |
| Vals Index | 53.2% | Default | Independent testIndependentVals.ai ↗ | 30 Sep 2026 | — | ±1.097 stderr; $0.202/test |
| Vals Public Benefits Bench v1.1 | 67.6% | Defaultvals id xiaomi/mimo-v2.6-flash | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | — | vals id xiaomi/mimo-v2.6-flash; rank 12/45; ±1.217 stderr; $0.031798/test |
| Vals SRE Bench | 4.2% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | — | ±1.241 stderr; $0.395/test |
| Vals Vibe Code Bench | 79.0% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | OpenHands | ±4.045 stderr; $0.563/test |