Models · Xiaomi MiMo · Out sinceReleased 21 Sep 2026
MiMo-V2.6-Pro#16 for research and analysis.#16 for research and analysis, best at its default setting.
MiMo-V2.6-Pro is made by Xiaomi MiMo. Among the models we track it ranks #16 for research and analysis, #26 for writing. 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.
- 45.7 / 100 · #26
- 70.3 / 100 · #16
- —
- Cheap$0.43 / $0.87
- $0.54
- 1.1M
- —
- 33 (33 independent33 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-pro.
Route it as xiaomi/mimo-v2.6-pro at $0.43 in / $0.87 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
- 1020B / 42B
- No
Needs one full AI server.
≤ 1.1 TB at 8-bit (one 8×H200 node). Weights ≈ 1071 GB at 8-bit, 561 GB at 4-bit (+10–30% for KV cache). MoE: 42B 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 (per HF safetensors dtypes). 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-Briefcase v1.1 | 1520 | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | |
| AA-LCR | 86.3% | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-LCR accuracy, AA-run (long multi-document reasoning) |
| AA-Omniscience Accuracy | 34.9% | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | |
| AA-Omniscience Hallucination Rate | 40.6% | DefaultMiMo-V2.6-Pro | 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 | 8.4 | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-Omniscience Index (-100..100): correct minus incorrect, abstentions not penalised |
| Artificial Analysis Intelligence Index | 46.3 | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug mimo-v2-6-pro; list price $0.435/0.87 per 1M in/out; cost to run AA Intelligence Index $0.13/task |
| Artificial Analysis output speed | 42 tok/s | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | tokens/sec (median output speed, first-party API); TTFT 4.3s; list price $0.435/0.87 per 1M in/out |
| GDPval-AA v2.1 | 1678 | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | 95% CI 1652.95-1703.64 |
| Humanity's Last Exam | 49.4% | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-run evaluation (AA slug mimo-v2-6-pro) |
| LLM Creative Story-Writing Benchmark (Lech Mazur) | 1.6 | DefaultXiaomi MiMo V2.6 Pro (thinking) | Independent testIndependentLech Mazur (LLM Creative Story-Writing Benchmark) ↗ | 28 Sep 2026 | — | rank 16/56; Thurstone comparison score (centered at 0); est. win chance 73%; 95% bootstrap 1.449 to 1.747; incomplete story set (see README coverage note) |
| LMArena Code Arena (WebDev) | 1619 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | Code Arena | WebDev overall (agentic web-dev, raw); rank 23 (CI rank 14-25); 95% CI 1606-1631; 2736 votes |
| LMArena Text - Coding category | 1540 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | text arena coding category, style control on; rank 8 (CI rank 1-43); 95% CI 1522-1558; 1101 votes |
| LMArena Text - Creative Writing | 1445 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 50 (rank range 13-88); 95% CI 1423.4-1466.0; 798 votes; style-controlled |
| LMArena Text - Expert | 1532 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 11 (rank range 1-53); 95% CI 1504.9-1559.5; 464 votes; style-controlled |
| LMArena Text - Hard Prompts | 1505 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 23 (rank range 7-49); 95% CI 1493.2-1516.5; 2607 votes; style-controlled |
| LMArena Text - Instruction Following | 1473 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 29 (rank range 8-63); 95% CI 1457.5-1489.0; 1382 votes; style-controlled |
| LMArena Text - Longer Query | 1495 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 20 (rank range 7-54); 95% CI 1479.9-1509.1; 1661 votes; style-controlled |
| LMArena Text - Multi-Turn | 1455 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 78 (rank range 21-128); 95% CI 1431.3-1479.5; 580 votes; style-controlled |
| LMArena Text - Non-English | 1461 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 40 (rank range 18-64); 95% CI 1449.3-1472.6; 2581 votes; style-controlled |
| LMArena Text - Occupational: Business, Management & Finance | 1461 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 55 (rank range 11-114); 95% CI 1438.9-1483.1; 717 votes; style-controlled |
| LMArena Text - Occupational: Legal & Government | 1468 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 59 (rank range 5-140); 95% CI 1435.7-1500.5; 348 votes; style-controlled |
| LMArena Text - Occupational: Writing, Literature & Language | 1457 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | rank 40 (rank range 12-77); 95% CI 1438.3-1475.6; 997 votes; style-controlled |
| LMArena Text (overall) | 1480 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | 30 Sep 2026 | — | text overall, style control on; rank 25 (CI rank 9-48); 95% CI 1470-1489; 4074 votes |
| ProgramBench (fully resolved) | 0.5% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | mini-SWE-agent | ±0.5 stderr; $0.727/test; strict fully-resolved rate |
| SciCode | 60.9% | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-run evaluation (AA slug mimo-v2-6-pro) |
| Terminal-Bench 4.0 | 34.8% | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA-run evaluation (AA slug mimo-v2-6-pro) |
| Terminal-Bench 4.0 | 31.3% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | mini-SWE-agent | ±3.072 stderr; $0.498/test |
| Vals Code Migration | 43.0% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | — | ±4.32 stderr; $0.692/test |
| Vals Index | 55.2% | Default | Independent testIndependentVals.ai ↗ | 30 Sep 2026 | — | ±1.182 stderr; $0.410/test |
| Vals Legal Research Bench | 47.1% | Defaultvals id xiaomi/mimo-v2.6-pro | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | — | vals id xiaomi/mimo-v2.6-pro; rank 13/72; ±3.469 stderr; $0.181201/test |
| Vals Public Benefits Bench v1.1 | 68.9% | Defaultvals id xiaomi/mimo-v2.6-pro | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | — | vals id xiaomi/mimo-v2.6-pro; rank 6/45; ±1.204 stderr; $0.081936/test |
| Vals SRE Bench | 3.0% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | — | ±1.065 stderr; $0.533/test |
| Vals Vibe Code Bench | 85.2% | Default | Independent testIndependentVals.ai ↗ | 29 Sep 2026 | OpenHands | ±3.392 stderr; $1.044/test |