MiMo-V2-Flash vs MiniMax M3.1 Flash
Full profiles: MiMo-V2-Flash (Xiaomi) and MiniMax M3.1 Flash (MiniMax): every benchmark, price and rank.
Updated · Data from 7 sources
As of 16 Nov 2026, MiMo-V2-Flash and MiniMax M3.1 Flash are neck and neck on quality (53.9 vs 54.3 on the BenchLeader Index, inside the ±7.7 margin), and MiMo-V2-Flash is 1.7× cheaper at $0.150 vs $0.262 per 1M tokens blended. Choose MiMo-V2-Flash for reasoning (56 vs 50) and agents & tools (58 vs 55); choose MiniMax M3.1 Flash for coding (55 vs 40) and long context (65 vs 60).
Key facts (as of 16 Nov 2026)
- MiMo-V2-Flash scores 53.9 on the BenchLeader Index and MiniMax M3.1 Flash scores 54.3 (BenchLeader, 16 Nov 2026).
- MiMo-V2-Flash costs $0.150 per 1M tokens blended (list price, 16 Nov 2026).
- MiniMax M3.1 Flash costs $0.262 per 1M tokens blended (list price, 16 Nov 2026).
- Of the 6 benchmarks both models have, MiniMax M3.1 Flash leads 5 (BenchLeader, 16 Nov 2026).
- On Arena WebDev, MiMo-V2-Flash is rated 1292 and MiniMax M3.1 Flash 1584 (LMArena, as published by 16 Nov 2026).
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 |
|---|---|---|---|
| Coding | MiniMax M3.1 Flash | 55 vs 40 category score; Arena WebDev 1584 vs 1292 | High |
| Agents & tool use | MiMo-V2-Flash | 58 vs 55 category score | Medium |
| Reasoning | MiMo-V2-Flash | 56 vs 50 category score; Humanity's Last Exam (AA) 22.9% vs 48.0% | Medium |
| Long documents | MiniMax M3.1 Flash | 65 vs 60 category score; AA-LCR v1.1 79.7% vs 70.7% | Medium |
| Chat quality (human preference) | – | Only MiMo-V2-Flash has an Arena rating (56 category score) | Not comparable |
| Lowest cost | MiMo-V2-Flash | $0.150 vs $0.262 per 1M blended; agentic coding session $0.007 vs $0.011 | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- MiMo-V2-Flash (thinking) and MiniMax M3.1 Flash are neck and neck on quality (53.9 vs 54.3, within the ±7.7 margin).
- MiMo-V2-Flash (thinking) is stronger in agents & tools, reasoning.
- MiniMax M3.1 Flash is stronger in coding, long context.
- MiMo-V2-Flash (thinking) is 1.7× cheaper ($0.150 vs $0.262 per 1M blended).
At a glance
| Spec | MiMo-V2-Flash | MiniMax M3.1 Flash |
|---|---|---|
| Developer | Xiaomi | MiniMax |
| Released | 16 Dec 2025 | 19 Oct 2026 |
| Context window (tokens) | 256,000 | 1,000,000 |
| Compared at | MiMo-V2-Flash (thinking) | MiniMax M3.1 Flash |
| Open weights | Yes | Yes |
| Price in / out / cached input per 1M | $0.100 / $0.300 / – | $0.150 / $0.600 / $0.015 |
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 | MiMo-V2-Flash (thinking) | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| Reasoning | 56.4 | 50.1 | MiMo-V2-Flash |
| Coding | 39.7 | 55.4 | MiniMax M3.1 Flash |
| Agents & tools | 58.1 | 55.2 | MiMo-V2-Flash |
| Maths | 54.3 | – | not comparable |
| Knowledge | – | 45.9 | not comparable |
| Instruction following | 63.9 | – | not comparable |
| Human preference | 55.5 | – | not comparable |
| Multimodal | – | 61.5 | not comparable |
| Long context | 59.8 | 64.5 | MiniMax M3.1 Flash |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Maths, Knowledge, Instruction following, Multimodal, Human preference.
Where sources disagree
Across the 6 benchmarks both have, MiMo-V2-Flash leads 1, MiniMax M3.1 Flash leads 5.
| Overall index | MiMo-V2-Flash (thinking) | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| BenchLeader Index | 53.9 | 54.3 | neck and neck |
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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | MiMo-V2-Flash (thinking) | MiniMax M3.1 Flash |
|---|---|---|
| Blended price per 1M tokens | $0.150 | $0.262 |
| Input / output per 1M | $0.100 / $0.300 | $0.150 / $0.600 |
| Cached input per 1M | – | $0.015 |
| Price per task: chat reply | $0.0001 | $0.0002 |
| Price per task: summarize a 30-page report | $0.0014 | $0.0022 |
| Price per task: code edit | $0.0011 | $0.0018 |
| Price per task: agentic coding session | $0.0072 | $0.011 |
| Price per task: structured extraction | $0.0003 | $0.0004 |
| Agentic coding session, input mostly cached | – | $0.0053 |
| Cost per benchmark task (AA Index) | – | $0.491 |
| Output tokens per task (AA Index) | – | 138k |
| Of which reasoning | – | 103k |
| Time per task (AA Index) | – | 15 min |
| Output speed | – | 151 tok/s |
| Time to first answer | – | 43.3 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 141.5 s |
Each model is compared at its best-ranked reasoning-effort setting. MiMo-V2-Flash (thinking) scores 53.9; MiMo-V2-Flash (no reasoning) scores 50.1. MiniMax M3.1 Flash scores 54.3 and takes 43 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
81 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | MiMo-V2-Flash (thinking) | MiniMax M3.1 Flash |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 53.9 | 54.3 |
| Agents & tools score | BenchLeader | 58.1 | 55.2 |
| Coding score | BenchLeader | 39.7 | 55.4 |
| Human preference score | BenchLeader | 55.5 | – |
| Instruction following score | BenchLeader | 63.9 | – |
| Long context score | BenchLeader | 59.8 | 64.5 |
| Maths score | BenchLeader | 54.3 | – |
| Reasoning score | BenchLeader | 56.4 | 50.1 |
| Knowledge score | BenchLeader | – | 45.9 |
| Multimodal score | BenchLeader | – | 61.5 |
| Blended price $/M | BenchLeader | $0.150 | $0.262 |
| Output speed | BenchLeader | – | 151 tok/s |
| Time to first answer | BenchLeader | – | 43.3 s |
| Context window | BenchLeader | 256,000 tokens | 1,000,000 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | 1411 | – |
| LiveBench 2.0 Reasoning | LiveBench | – | 82.9%† |
| GPQA Diamond (AA) | Artificial Analysis | 84.7% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 22.9% | 48.0% |
| HLE-Diamond (AA) | Artificial Analysis | – | 28.1% |
| GPQA Diamond (Vals) | Vals AI | 59.3%† | – |
| CritPt | Artificial Analysis | 4.3% | 22.3% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 32.5% |
| Arena Expert | Arena (LMArena) | 1414 | – |
| Coding | |||
| SciCode | SciCode | 25.9%† | – |
| Arena Coding | Arena (LMArena) | 1432 | – |
| Arena WebDev | Arena (LMArena) | 1292 | 1584 |
| LiveBench 2.0 Coding | LiveBench | – | 68.8%† |
| SciCode (AA) | Artificial Analysis | – | 53.4% |
| Vibe Code Bench v1.1 | Vals AI | – | 73.9%† |
| Vibe Code Bench 1-100 v1.1 | Vals AI | – | 19.8%† |
| SWE-Bench Pro V2 | Scale AI SEAL | – | 96.6%† |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | – | 84.3%† |
| ALE-Bench | Epoch AI Benchmarking Hub | 738.0† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 25.8% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 61.8%† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 30.3† |
| Design Arena Website | Design Arena | 1159† | 1277 |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 38.6% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 20.8% |
Show all 81 benchmarks
| Metric | Publisher | MiMo-V2-Flash (thinking) | MiniMax M3.1 Flash |
|---|---|---|---|
| Coding | |||
| LiveCodeBench (AA) | Artificial Analysis | 86.8% | – |
| Agents & tools | |||
| Arena Agent | Arena (LMArena) | – | -2.7 |
| LiveBench Long Agentic | LiveBench | – | 25.7%† |
| LiveBench Browser | LiveBench | – | 80.6%† |
| Terminal-Bench Hard | Artificial Analysis | 28.0% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 95.0% | – |
| HiL-Bench | Scale AI SEAL | – | 65.7% |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 47.9% |
| GDPval-AA v2.1 | Artificial Analysis | 636† | 1465 |
| Finance Agent v2.1 | Vals AI | – | 58.8%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 7.5%† |
| Legal Research Bench | Vals AI | – | 34.1%† |
| Tax Agent Bench | Vals AI | – | 32.1%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 25.3%† |
| Arena Agent Task Completion | Arena (LMArena) | – | -0.7 |
| AutomationBench | Artificial Analysis | – | 72.5% |
| GDP.pdf (AA) | Artificial Analysis | – | 20.8% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1474 |
| GDPx | GDPx by SemiAnalysis | – | 4.0%† |
| Design Arena Agentic | Design Arena | – | 1252 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 3.3% |
| MKA (AA) | Artificial Analysis | – | 33.5% |
| Maths | |||
| Arena Maths | Arena (LMArena) | 1372 | – |
| AIME 2025 (AA) | Artificial Analysis | 96.3% | – |
| Knowledge | |||
| LiveBench 2.0 Data Analysis | LiveBench | – | 71.4%† |
| LiveBench Research | LiveBench | – | 76.7%† |
| AA-Omniscience v1.1 | Artificial Analysis | – | -6.4 |
| PRBench Finance | Scale AI SEAL | – | 45.6% |
| PRBench Legal | Scale AI SEAL | – | 45.1% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 67.8%† |
| Access to Justice Benchmark | Vals AI | – | 73.3%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 45.1% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 6.3% |
| Global-MMLU-Lite (AA) | Artificial Analysis | 84.4% | – |
| Instruction following | |||
| IFBench | Artificial Analysis | 64.2% | – |
| Arena Instruction Following | Arena (LMArena) | 1375 | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1386 | – |
| Arena Creative Writing | Arena (LMArena) | 1336 | – |
| Arena Multi-turn | Arena (LMArena) | 1375 | – |
| Arena Longer Queries | Arena (LMArena) | 1401 | – |
| Multimodal | |||
| LiveBench Design | LiveBench | – | 71.2%† |
| MMMU-Pro | Artificial Analysis | – | 79.1% |
| SAGE | Vals AI | – | 85.3%† |
| VIALS-AA | Handshake AI | – | 29.8% |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 70.7% | 79.7% |
| MLCR | Artificial Analysis | – | 16.7% |
| Composite | |||
| LiveBench 2.0 | LiveBench | – | 63.7%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 29.1 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 20.8 | 42.7 |
| AA Progress Index v1 | Artificial Analysis | 264.7 | 317.6 |
| Vals Index | Vals AI | – | 53.8† |
| Vals Finance Index | Vals AI | – | 55.9%† |
| Vals Router Index | Vals AI | – | 53.8% |
| Vals Legal Index | Vals AI | – | 67.1%† |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 52.1% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 52.8 | 27.8 |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- MiniMax M3.1 Flash: BenchLeader Index 53.7 → 54.3.
- MiMo-V2-Flash (thinking): 2 new results (Global-MMLU-Lite (AA), AIME 2025 (AA)).
- MiniMax M3.1 Flash: BenchLeader Index 54.3 → 53.7.
- MiniMax M3.1 Flash: 1 score revision.
- MiniMax M3.1 Flash: 6 score revisions.
- MiniMax M3.1 Flash: BenchLeader Index 53.0 → 54.3.
- MiniMax M3.1 Flash: 1 new result (HiL-Bench).
- MiniMax M3.1 Flash: BenchLeader Index 52.0 → 53.0.
- MiniMax M3.1 Flash: 2 new results (PRBench Finance, PRBench Legal).
- MiniMax M3.1 Flash: 1 score revision.
Related comparisons
- MiniMax M3.1 Flash vs Claude Opus 5.5
- MiniMax M3.1 Flash vs GPT-6 Astra
- MiniMax M3.1 Flash vs Claude Fable 5.1
- MiniMax M3.1 Flash vs GPT-6.1 Sol
- MiniMax M3.1 Flash vs Gemini 4 Argon
- MiniMax M3.1 Flash vs GPT-5.6 Sol
- MiniMax M3.1 Flash vs Claude Sonnet 5.5
- MiniMax M3.1 Flash vs Muse Wonder Full
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
MiMo-V2-Flash vs MiniMax M3.1 Flash: questions
- Is MiMo-V2-Flash better than MiniMax M3.1 Flash?
- MiMo-V2-Flash (thinking) and MiniMax M3.1 Flash are neck and neck on quality (53.9 vs 54.3, within the ±7.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
- MiMo-V2-Flash vs MiniMax M3.1 Flash: which is cheaper, and will that change?
- MiMo-V2-Flash is cheaper today: $0.150 against $0.262 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is MiMo-V2-Flash or MiniMax M3.1 Flash better for coding?
- MiniMax M3.1 Flash scores higher in coding (55 vs 40 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1292 for MiMo-V2-Flash against 1584 for MiniMax M3.1 Flash.
- Is MiMo-V2-Flash or MiniMax M3.1 Flash better for agents and tool use?
- MiMo-V2-Flash scores higher in agentic tasks (58 vs 55 on the category index, where 50 is average).
- Which is better for long documents?
- MiniMax M3.1 Flash scores higher on long-context benchmarks (65 vs 60). MiniMax M3.1 Flash accepts more context: 1,000,000 against 256,000 tokens for MiMo-V2-Flash.
More questions (2)
- Do independent benchmarks agree on MiMo-V2-Flash vs MiniMax M3.1 Flash?
- Across the 6 benchmarks both have, MiMo-V2-Flash leads 1, MiniMax M3.1 Flash leads 5.
- When was MiniMax M3.1 Flash released?
- MiniMax M3.1 Flash was released on 19 Oct 2026.