Kimi K3.1 Pro vs MiMo-V2.6-Pro
Full profiles: Kimi K3.1 Pro (Moonshot AI) and MiMo-V2.6-Pro (Xiaomi): every benchmark, price and rank.
Updated · Data from 7 sources
As of 24 Oct 2026, Kimi K3.1 Pro and MiMo-V2.6-Pro are neck and neck on quality (66.8 vs 64.0 on the BenchLeader Index, inside the ±7.5 margin of error), and MiMo-V2.6-Pro costs 7.3× less, which makes it the better buy for most workloads. Kimi K3.1 Pro leads in every category we measure both in.
Kimi K3.1 Pro benchmarks 
MiMo-V2.6-Pro benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Agents & tool use | Kimi K3.1 Pro | 67 vs 58 category score; DeepSec-Bench (AA) 36.7% vs 26.2% | High |
| Reasoning | Kimi K3.1 Pro | 81 vs 79 category score; CritPt 24.6% vs 26.6% | Medium |
| Knowledge | Kimi K3.1 Pro | 75 vs 65 category score; AA-Omniscience 29.5 vs 8.4 | High |
| Long documents | Either | 68 vs 68 category score; AA-LCR 86.3% vs 86.3% | Either |
| Images and other media | Kimi K3.1 Pro | 67 vs 60 category score; LiveBench Design 77.8% vs 78.5% | Medium |
| Chat quality (human preference) | – | Only MiMo-V2.6-Pro has an Arena rating (67 category score) | Not comparable |
| Lowest cost | MiMo-V2.6-Pro | $0.548 vs $4.00 per 1M blended; agentic coding session $0.030 vs $0.160 | – |
| Fastest first answer | Kimi K3.1 Pro | 27.7 s (Kimi K3.1 Pro) vs 39.8 s (MiMo-V2.6-Pro) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Kimi K3.1 Pro and MiMo-V2.6-Pro are neck and neck on quality (66.8 vs 64.0, within the ±7.5 margin).
- Kimi K3.1 Pro is stronger in agents & tools, composite, knowledge, multimodal, reasoning.
- MiMo-V2.6-Pro is stronger in coding, human preference, maths.
- MiMo-V2.6-Pro is 7.3× cheaper ($0.548 vs $4.00 per 1M blended).
- Kimi K3.1 Pro streams 1.5× faster (81 vs 54 tokens per second).
At a glance
| Spec | Kimi K3.1 Pro | MiMo-V2.6-Pro |
|---|---|---|
| Developer | Moonshot AI | Xiaomi |
| Released | 23 Oct 2026 | 21 Sept 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Kimi K3.1 Pro | MiMo-V2.6-Pro |
| Open weights | No | Yes |
| Price in / out / cached input per 1M | $2.00 / $10.00 / $0.200 | $0.440 / $0.870 / $0.0036 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Kimi K3.1 Pro | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| Reasoning | 81.3 | 78.7 | Kimi K3.1 Pro |
| Coding | – | 61.6 | not comparable |
| Agents & tools | 67.3 | 58.3 | Kimi K3.1 Pro |
| Maths | – | 66.0 | not comparable |
| Knowledge | 74.8 | 65.3 | Kimi K3.1 Pro |
| Human preference | – | 67.1 | not comparable |
| Multimodal | 67.0 | 59.8 | Kimi K3.1 Pro |
| Long context | 68.3 | 68.3 | level |
| Composite | 75.8 | 69.8 | Kimi K3.1 Pro |
Where sources disagree
Across the 25 benchmarks both have, Kimi K3.1 Pro leads 18, MiMo-V2.6-Pro leads 6 and 1 is a tie. Every overall index that rates both puts Kimi K3.1 Pro ahead.
| Overall index | Kimi K3.1 Pro | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 66.8 | 64.0 | neck and neck |
| AA Intelligence Index v4.3.2 | 55.1 | 46.3 | Kimi K3.1 Pro |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | Kimi K3.1 Pro | MiMo-V2.6-Pro |
|---|---|---|
| Blended price per 1M tokens | $4.00 | $0.548 |
| Input / output per 1M | $2.00 / $10.00 | $0.440 / $0.870 |
| Cached input per 1M | $0.200 | $0.0036 |
| Price per task: chat reply | $0.0038 | $0.0004 |
| Price per task: summarize a 30-page report | $0.030 | $0.0058 |
| Price per task: code edit | $0.027 | $0.0039 |
| Price per task: agentic coding session | $0.160 | $0.030 |
| Price per task: structured extraction | $0.0060 | $0.0011 |
| Cost to run a full benchmark suite | $2.11 | $0.133 |
| Output speed | 81 tok/s | 54 tok/s |
| Time to first answer | 27.7 s | 39.8 s |
| Time to a complete answer | 33.9 s | 49.1 s |
Per token is not per task: on Artificial Analysis' full suite Kimi K3.1 Pro cost $2.11 and MiMo-V2.6-Pro $0.133, because Kimi K3.1 Pro used about 2.2× as many tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. Kimi K3.1 Pro scores 66.8 and takes 28 s to its first answer token. MiMo-V2.6-Pro scores 64.0 and takes 40 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
74 benchmarks, grouped by category; each name links to the board and its leaders.
| Metric | Publisher | Kimi K3.1 Pro | MiMo-V2.6-Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 66.8 | 64.0 |
| Agents & tools score | BenchLeader | 67.3 | 58.3 |
| Composite score | BenchLeader | 75.8 | 69.8 |
| Knowledge score | BenchLeader | 74.8 | 65.3 |
| Long context score | BenchLeader | 68.3 | 68.3 |
| Multimodal score | BenchLeader | 67.0 | 59.8 |
| Reasoning score | BenchLeader | 81.3 | 78.7 |
| Coding score | BenchLeader | – | 61.6 |
| Human preference score | BenchLeader | – | 67.1 |
| Maths score | BenchLeader | – | 66.0 |
| Blended price $/M | BenchLeader | $4.00 | $0.548 |
| Output speed | BenchLeader | 81 tok/s | 54 tok/s |
| Time to first answer | BenchLeader | 27.7 s | 39.8 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | – | 1504 |
| LiveBench 2.0 Reasoning | LiveBench | 91.1% | 79.6% |
| Humanity's Last Exam (AA) | Artificial Analysis | 52.5% | 49.4% |
| CritPt | Artificial Analysis | 24.6% | 26.6% |
| MysteryMechanism | Vals AI | – | 15.3% |
| Coding | |||
| SciCode | SciCode | – | 60.9% |
| Arena Coding | Arena (LMArena) | – | 1538 |
| Arena WebDev | Arena (LMArena) | – | 1625 |
| LiveBench 2.0 Coding | LiveBench | 81.8% | 81.5% |
| SciCode (AA) | Artificial Analysis | 60.8% | 60.9% |
| IOI | Vals AI | – | 39.3% |
| Code Migration | Vals AI | – | 43.0% |
| Code Migration v1.1 | Vals AI | – | 48.8% |
| ProgramBench | Vals AI | – | 0.5% |
| SWE-bench Multimodal | Vals AI | – | 41.3% |
| Vibe Code Bench v1.1 | Vals AI | – | 85.2% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 1158.1 |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 67.2% | 34.9% |
| FrontierCode 1.1 (AA) | Artificial Analysis | 47.1% | 45.4% |
| Agents & tools | |||
| APEX-Agents | Mercor | – | 54.4% |
| Arena Agent | Arena (LMArena) | – | 3.7 |
| LiveBench Long Agentic | LiveBench | 49.5% | 47.5% |
| LiveBench Browser | LiveBench | 80.0% | 88.0% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 67.8% |
| GDPval-AA v2.1 | Artificial Analysis | 67.3% | 59.1% |
Show all 74 benchmarks
| Metric | Publisher | Kimi K3.1 Pro | MiMo-V2.6-Pro |
|---|---|---|---|
| Agents & tools | |||
| Analyst Agent (AA) | Artificial Analysis | – | 37.5% |
| CyberBench | Vals AI | – | 72.9% |
| Finance Agent v2 | Vals AI | – | 57.3% |
| Finance Agent v2.1 | Vals AI | – | 64.3% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 13.8% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 10.8% |
| Legal Research Bench | Vals AI | – | 47.1% |
| SREBench | Vals AI | – | 3.0% |
| Tax Agent Bench | Vals AI | – | 32.4% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 31.3% |
| Terminal-Bench Science | Vals AI | – | 2.9% |
| AutomationBench | Artificial Analysis | 73.3% | 58.6% |
| GDP.pdf (AA) | Artificial Analysis | 31.4% | 19.2% |
| AA-Briefcase v1.1 | Artificial Analysis | 1678 | 1512 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 5.7% |
| CWE-Bench (AA) | Artificial Analysis | 60.8% | 63.3% |
| DeepSec-Bench (AA) | Artificial Analysis | 36.7% | 26.2% |
| CyberGym end-to-end (AA) | Artificial Analysis | 94.7% | 78.6% |
| Maths | |||
| ProofBench | Vals AI | – | 70.0% |
| Arena Maths | Arena (LMArena) | – | 1489 |
| Knowledge | |||
| LiveBench 2.0 Data Analysis | LiveBench | 79.1% | 72.3% |
| LiveBench Research | LiveBench | 77.9% | 76.7% |
| AA-Omniscience | Artificial Analysis | 29.5 | 8.4 |
| Excel Modeling Benchmark | Vals AI | – | 62.9% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 67.3% |
| MedCode | Vals AI | – | 45.0% |
| MedScribe | Vals AI | – | 88.3% |
| Public Benefits Bench v1.1 | Vals AI | – | 68.9% |
| AA-Omniscience: accuracy | Artificial Analysis | 51.0% | 34.9% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 56.1% | 59.4% |
| Instruction following | |||
| Arena Instruction Following | Arena (LMArena) | – | 1471 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1480 |
| Arena Creative Writing | Arena (LMArena) | – | 1446 |
| Arena Multi-turn | Arena (LMArena) | – | 1457 |
| Arena Longer Queries | Arena (LMArena) | – | 1494 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1263 |
| LiveBench Design | LiveBench | 77.8% | 78.5% |
| MMMU-Pro | Artificial Analysis | 83.9% | – |
| SAGE | Vals AI | – | 45.0% |
| AA-3D | Artificial Analysis | – | 980 |
| Long context | |||
| AA-LCR | Artificial Analysis | 86.3% | 86.3% |
| MLCR | Artificial Analysis | – | 12.8% |
| Composite | |||
| LiveBench 2.0 | LiveBench | 76.7% | 74.9% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 55.1 | 46.3 |
| Vals Index | Vals AI | – | 57.8 |
| Vals Finance Index | Vals AI | – | 57.9% |
| Vals Router Index | Vals AI | – | 57.8% |
| AA Cyber Index | Artificial Analysis | 64.1 | 56.1 |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 52.8 |
Data as of 2026-10-24. Best configuration of each model; every score links to its source on the model pages.
What changed
- Kimi K3.1 Pro: BenchLeader Index 65.6 → 66.8.
- Kimi K3.1 Pro: 5 new results (FrontierCode 1.1 (AA), AA Cyber Index, CWE-Bench (AA)…).
- Kimi K3.1 Pro: first results.
- MiMo-V2.6-Pro: 7 new results (Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…).
- MiMo-V2.6-Pro: 1 score revision.
- MiMo-V2.6-Pro: 3 score revisions.
- MiMo-V2.6-Pro: BenchLeader Index 65.4 → 64.2.
- MiMo-V2.6-Pro: 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…); 1 score revision.
- MiMo-V2.6-Pro: 1 score revision.
- MiMo-V2.6-Pro: 1 score revision.
Related comparisons
- Kimi K3.1 Pro vs Claude Opus 5.5
- Kimi K3.1 Pro vs Gemini 4 Argon
- Kimi K3.1 Pro vs Muse Wonder Full
- MiMo-V2.6-Pro vs Claude Opus 5.5
- MiMo-V2.6-Pro vs Gemini 4 Argon
- MiMo-V2.6-Pro vs Muse Wonder Full
- MiMo-V2.6-Pro vs Claude Fable 5.1
- Kimi K3 vs MiMo-V2.6-Pro
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Kimi K3.1 Pro vs MiMo-V2.6-Pro: questions
- Is Kimi K3.1 Pro better than MiMo-V2.6-Pro?
- Kimi K3.1 Pro and MiMo-V2.6-Pro are neck and neck on quality (66.8 vs 64.0, within the ±7.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-24, so check the category scores for your use.
- Which is cheaper, Kimi K3.1 Pro or MiMo-V2.6-Pro, and will that change?
- MiMo-V2.6-Pro is cheaper today: $0.548 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Kimi K3.1 Pro better than MiMo-V2.6-Pro for agents and tool use?
- Kimi K3.1 Pro scores higher in agentic tasks (67 vs 58 on the category index, where 50 is average). On CWE-Bench (AA), the top shared agents & tools benchmark, it is 60.8% for Kimi K3.1 Pro against 63.3% for MiMo-V2.6-Pro.
- Which is better for long documents?
- They are level on long-context benchmarks (68 vs 68). Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Kimi K3.1 Pro answers first: 27.7 s against 39.8 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Which is faster, Kimi K3.1 Pro or MiMo-V2.6-Pro?
- Kimi K3.1 Pro streams faster: 81 against 54 output tokens per second.
- Do independent benchmarks agree on Kimi K3.1 Pro vs MiMo-V2.6-Pro?
- Across the 25 benchmarks both have, Kimi K3.1 Pro leads 18, MiMo-V2.6-Pro leads 6 and 1 is a tie. Every overall index that rates both puts Kimi K3.1 Pro ahead.
- When was Kimi K3.1 Pro released?
- Kimi K3.1 Pro was released on 23 Oct 2026.