MiniMax M3.1 Flash vs Mistral Large 4
Full profiles: MiniMax M3.1 Flash (MiniMax) and Mistral Large 4 (Mistral AI): every benchmark, price and rank.
Updated · Data from 8 sources
As of 16 Nov 2026, MiniMax M3.1 Flash and Mistral Large 4 are neck and neck on quality (54.3 vs 52.9 on the BenchLeader Index, inside the ±6.4 margin), and MiniMax M3.1 Flash is 4.0× cheaper at $0.262 vs $1.05 per 1M tokens blended. MiniMax M3.1 Flash leads in every category we measure both in. MiniMax M3.1 Flash streams faster.
Key facts (as of 16 Nov 2026)
- MiniMax M3.1 Flash scores 54.3 on the BenchLeader Index and Mistral Large 4 scores 52.9 (BenchLeader, 16 Nov 2026).
- MiniMax M3.1 Flash costs $0.262 per 1M tokens blended (list price, 16 Nov 2026).
- Mistral Large 4 costs $1.05 per 1M tokens blended (list price, 16 Nov 2026).
- MiniMax M3.1 Flash streams faster than Mistral Large 4 (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 26 benchmarks both models have, MiniMax M3.1 Flash leads 19 (BenchLeader, 16 Nov 2026).
- On Arena WebDev, MiniMax M3.1 Flash is rated 1584 and Mistral Large 4 1565 (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 54 category score; Arena WebDev 1584 vs 1565 | Medium |
| Agents & tool use | MiniMax M3.1 Flash | 55 vs 49 category score; Arena Agent -2.7 vs -5.4 | Medium |
| Reasoning | MiniMax M3.1 Flash | 50 vs 46 category score; HLE-Diamond (AA) 28.1% vs 15.1% | Medium |
| Knowledge | MiniMax M3.1 Flash | 46 vs 41 category score; AA-Omniscience v1.1 -6.4 vs -7.5 | Medium |
| Long documents | Either | 65 vs 65 category score; AA-LCR v1.1 79.7% vs 81.3% | Either |
| Images and other media | MiniMax M3.1 Flash | 62 vs 58 category score; MMMU-Pro 79.1% vs 76.4% | Medium |
| Chat quality (human preference) | – | Only Mistral Large 4 has an Arena rating (60 category score) | Not comparable |
| Lowest cost | MiniMax M3.1 Flash | $0.262 vs $1.05 per 1M blended; agentic coding session $0.011 vs $0.050 | – |
| Fastest first answer | Either | 43.3 s (MiniMax M3.1 Flash) vs 40.9 s (Mistral Large 4) 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
- MiniMax M3.1 Flash and Mistral Large 4 are neck and neck on quality (54.3 vs 52.9, within the ±6.4 margin).
- MiniMax M3.1 Flash is stronger in agents & tools, coding, knowledge, multimodal, reasoning.
- Mistral Large 4 is stronger in long context.
- MiniMax M3.1 Flash is 4.0× cheaper ($0.262 vs $1.05 per 1M blended).
- MiniMax M3.1 Flash streams 1.6× faster (151 vs 97 tokens per second).
At a glance
| Spec | MiniMax M3.1 Flash | Mistral Large 4 |
|---|---|---|
| Developer | MiniMax | Mistral AI |
| Released | 19 Oct 2026 | 6 Oct 2026 |
| Context window (tokens) | 1,000,000 | 1,048,576 |
| Compared at | MiniMax M3.1 Flash | Mistral Large 4 |
| Open weights | Yes | Yes |
| Price in / out / cached input per 1M | $0.150 / $0.600 / $0.015 | $0.700 / $2.10 / $0.070 |
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 | MiniMax M3.1 Flash | Mistral Large 4 | Leader |
|---|---|---|---|
| Reasoning | 50.1 | 46.2 | MiniMax M3.1 Flash |
| Coding | 55.4 | 53.8 | MiniMax M3.1 Flash |
| Agents & tools | 55.2 | 48.8 | MiniMax M3.1 Flash |
| Maths | – | 54.2 | not comparable |
| Knowledge | 45.9 | 40.7 | MiniMax M3.1 Flash |
| Human preference | – | 59.7 | not comparable |
| Multimodal | 61.5 | 58.0 | MiniMax M3.1 Flash |
| Long context | 64.5 | 65.3 | level |
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, Instruction following, Human preference.
Where sources disagree
Across the 26 benchmarks both have, MiniMax M3.1 Flash leads 19, Mistral Large 4 leads 7. Every overall index that rates both puts MiniMax M3.1 Flash ahead.
| Overall index | MiniMax M3.1 Flash | Mistral Large 4 | Leader |
|---|---|---|---|
| BenchLeader Index | 54.3 | 52.9 | neck and neck |
| AA Intelligence Index v5.0.1 | 29.1 | 25.3 | MiniMax M3.1 Flash |
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 | MiniMax M3.1 Flash | Mistral Large 4 |
|---|---|---|
| Blended price per 1M tokens | $0.262 | $1.05 |
| Input / output per 1M | $0.150 / $0.600 | $0.700 / $2.10 |
| Cached input per 1M | $0.015 | $0.070 |
| Price per task: chat reply | $0.0002 | $0.0009 |
| Price per task: summarize a 30-page report | $0.0022 | $0.0097 |
| Price per task: code edit | $0.0018 | $0.0074 |
| Price per task: agentic coding session | $0.011 | $0.050 |
| Price per task: structured extraction | $0.0004 | $0.0018 |
| Agentic coding session, input mostly cached | $0.0053 | $0.022 |
| Cost per benchmark task (AA Index) | $0.491 | $4.21 |
| Output tokens per task (AA Index) | 138k | 135k |
| Of which reasoning | 103k | 102k |
| Time per task (AA Index) | 15 min | 23 min |
| Output speed | 151 tok/s | 97 tok/s |
| Time to first answer | 43.3 s | 40.9 s |
| Time to a complete answer, last measured 13 Nov 2026 | 141.5 s | 119.0 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.491 on MiniMax M3.1 Flash and $4.21 on Mistral Large 4, and MiniMax M3.1 Flash wrote 1.0× as many output tokens for the same work.
Each model is compared at its best-ranked reasoning-effort setting. MiniMax M3.1 Flash scores 54.3 and takes 43 s to its first answer token. Mistral Large 4 scores 52.9 and takes 41 s to its first answer token; Mistral Large 4 (high) scores 48.3 in 45 s, Mistral Large 4 (medium) scores 45.9 in 27 s. 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
123 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 | MiniMax M3.1 Flash | Mistral Large 4 |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 54.3 | 52.9 |
| Agents & tools score | BenchLeader | 55.2 | 48.8 |
| Coding score | BenchLeader | 55.4 | 53.8 |
| Knowledge score | BenchLeader | 45.9 | 40.7 |
| Long context score | BenchLeader | 64.5 | 65.3 |
| Multimodal score | BenchLeader | 61.5 | 58.0 |
| Reasoning score | BenchLeader | 50.1 | 46.2 |
| Human preference score | BenchLeader | – | 59.7 |
| Maths score | BenchLeader | – | 54.2 |
| Blended price $/M | BenchLeader | $0.262 | $1.05 |
| Output speed | BenchLeader | 151 tok/s | 97 tok/s |
| Time to first answer | BenchLeader | 43.3 s | 40.9 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 88.1%† |
| Arena Hard Prompts | Arena (LMArena) | – | 1453 |
| LiveBench 2.0 Reasoning | LiveBench | 82.9%† | 85.2%† |
| LiveBench 1.0 Reasoning | LiveBench | – | 83.9%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 48.0% | 35.0% |
| HLE-Diamond (AA) | Artificial Analysis | 28.1% | 15.1% |
| CritPt | Artificial Analysis | 22.3% | 10.6% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 32.5% | 24.5% |
| MysteryMechanism | Vals AI | – | 12.2%† |
| Arena Expert | Arena (LMArena) | – | 1464 |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 33.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 17.0%† |
| LMCA | Epoch AI Benchmarking Hub | – | 35.8% |
| DTBench | Epoch AI Benchmarking Hub | – | 88.2% |
| Coding | |||
| SciCode | SciCode | – | 54.2% |
| FrontierCode | Cognition | – | 39.4%† |
| Arena Coding | Arena (LMArena) | – | 1484 |
| Arena WebDev | Arena (LMArena) | 1584 | 1565 |
| LiveBench 2.0 Coding | LiveBench | 68.8%† | 79.4%† |
| LiveBench 1.0 Coding | LiveBench | – | 77.2%† |
| SciCode (AA) | Artificial Analysis | 53.4% | 54.2% |
| IOI | Vals AI | – | 45.3%† |
| Code Migration | Vals AI | – | 30.6%† |
| SWE-bench Multimodal | Vals AI | – | 33.1%† |
| Vibe Code Bench 1-100 | Vals AI | – | 14.3%† |
Show all 123 benchmarks
| Metric | Publisher | MiniMax M3.1 Flash | Mistral Large 4 |
|---|---|---|---|
| Coding | |||
| Vibe Code Bench v1.1 | Vals AI | 73.9%† | 78.4%† |
| Vibe Code Bench 1-100 v1.1 | Vals AI | 19.8%† | – |
| SWE Atlas v1.1 | Scale AI SEAL | – | 45.2% |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 61.3% |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 40.0% |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 34.3% |
| SWE-Bench Pro V2 | Scale AI SEAL | 96.6%† | – |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | 84.3%† | – |
| MirrorCode | Epoch AI Benchmarking Hub | – | 40.0%† |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | – | 28.1% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 1213.2 |
| WeirdML v3 | WeirdML | – | 4.5%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 25.8% | 26.8% |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 30.3† | 57.6† |
| Design Arena Website | Design Arena | 1277 | 1258 |
| FrontierCode 1.1 (AA) | Artificial Analysis | 38.6% | 41.5% |
| FrontierCode 2.0 (AA) | Artificial Analysis | 20.8% | 13.6% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 27.6%† |
| APEX-Agents | Mercor | – | 51.6%† |
| Arena Agent | Arena (LMArena) | -2.7 | -5.4 |
| LiveBench Long Agentic | LiveBench | 25.7%† | 24.7%† |
| LiveBench Browser | LiveBench | 80.6%† | 17.4%† |
| LiveBench Agentic Coding | LiveBench | – | 57.2%† |
| HiL-Bench | Scale AI SEAL | 65.7% | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 47.9% | 46.1% |
| GDPval-AA v2.1 | Artificial Analysis | 1465 | 1431 |
| Finance Agent v2 | Vals AI | – | 54.7%† |
| Finance Agent v2.1 | Vals AI | 58.8%† | 61.4%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 7.5%† | 17.5%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 15.8%† |
| Legal Research Bench | Vals AI | 34.1%† | 31.7%† |
| Tax Agent Bench | Vals AI | 32.1%† | 30.4%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 25.3%† | 27.8%† |
| Arena Agent Task Completion | Arena (LMArena) | -0.7 | -4.7 |
| AutomationBench | Artificial Analysis | 72.5% | 59.9% |
| GDP.pdf (AA) | Artificial Analysis | 20.8% | 18.6% |
| Harvey LAB-AA v1.1 | Harvey | – | 3.1% |
| AA-Briefcase v1.1 | Artificial Analysis | 1474 | 1393 |
| GDPx | GDPx by SemiAnalysis | 4.0%† | – |
| Design Arena Agentic | Design Arena | 1252 | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 3.3% | 4.8% |
| CWE-Bench (AA) | Artificial Analysis | – | 50.8% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 16.0% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 81.7% |
| MKA (AA) | Artificial Analysis | 33.5% | 35.1%† |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 58.6%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 26.8%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 98.3%† |
| ProofBench | Vals AI | – | 10.0% |
| LiveBench Mathematics | LiveBench | – | 93.6%† |
| Arena Maths | Arena (LMArena) | – | 1459 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 20.0%† |
| LiveBench 2.0 Data Analysis | LiveBench | 71.4%† | 76.6%† |
| LiveBench Research | LiveBench | 76.7%† | 80.3%† |
| LiveBench 1.0 Data Analysis | LiveBench | – | 76.5%† |
| AA-Omniscience v1.1 | Artificial Analysis | -6.4 | -7.5 |
| PRBench Finance | Scale AI SEAL | 45.6% | – |
| PRBench Legal | Scale AI SEAL | 45.1% | – |
| BioMysteryBench | Vals AI | – | 67.0%† |
| Excel Modeling Benchmark | Vals AI | – | 56.2%† |
| Excel Modeling Benchmark v1.1 | Vals AI | 67.8%† | 69.0%† |
| MedCode | Vals AI | – | 40.7%† |
| MedScribe | Vals AI | – | 80.4%† |
| Access to Justice Benchmark | Vals AI | 73.3%† | – |
| Immigration Bench | Vals AI | – | 63.7%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 45.1% | 23.9% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 6.3% | 58.7% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 49.6%† |
| LiveBench Instruction Following | LiveBench | – | 64.8%† |
| Arena Instruction Following | Arena (LMArena) | – | 1418 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1420 |
| Arena Creative Writing | Arena (LMArena) | – | 1359 |
| Arena Multi-turn | Arena (LMArena) | – | 1429 |
| Arena Longer Queries | Arena (LMArena) | – | 1420 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1244 |
| LiveBench Design | LiveBench | 71.2%† | 76.3%† |
| MMMU-Pro | Artificial Analysis | 79.1% | 76.4% |
| SAGE | Vals AI | 85.3%† | – |
| Furniture Assembly | Epoch AI Benchmarking Hub | – | 20.8%† |
| VIALS-AA | Handshake AI | 29.8% | 20.5%† |
| Code2Video-AA | Artificial Analysis | – | 931 |
| AA-3D | Artificial Analysis | – | 882 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 79.7% | 81.3% |
| MLCR | Artificial Analysis | 16.7% | 7.8% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 154.6 |
| LiveBench 2.0 | LiveBench | 63.7%† | 60.3%† |
| LiveBench 1.0 | LiveBench | – | 71.8%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 29.1 | 25.3 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 42.7 | 38.4 |
| AA Progress Index v1 | Artificial Analysis | 317.6 | 312.4 |
| Vals Index | Vals AI | 53.8† | – |
| Vals Finance Index | Vals AI | 55.9%† | 56.9%† |
| Vals Router Index | Vals AI | 53.8% | – |
| Vals Legal Index | Vals AI | 67.1%† | 65.6%† |
| AA Cyber Index | Artificial Analysis | – | 49.5 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 52.1% | 23.1% |
| DistressBench | Scale AI SEAL | – | 77.0% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 27.8 | 38.9† |
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.
- Mistral Large 4: BenchLeader Index 52.2 → 52.9.
- Mistral Large 4: 1 new result (GDPval-AA v2.1).
- Mistral Large 4: 1 score revision.
- Mistral Large 4: 2 score revisions.
- MiniMax M3.1 Flash: BenchLeader Index 54.3 → 53.7.
- MiniMax M3.1 Flash: 1 score revision.
- Mistral Large 4: 6 score revisions.
- Mistral Large 4: BenchLeader Index 52.7 → 52.2.
- MiniMax M3.1 Flash: 6 score revisions.
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
- Mistral Large 4 vs Muse Spark 1.3
- Mistral Large 4 vs Muse Ember
- Mistral Large 4 vs Mistral Large 4.0 OSS
- MiniMax M3.1 Flash vs Gemini 4 Argon
- MiniMax M3.1 Flash vs GPT-5.6 Sol
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
MiniMax M3.1 Flash vs Mistral Large 4: questions
- Is MiniMax M3.1 Flash better than Mistral Large 4?
- MiniMax M3.1 Flash and Mistral Large 4 are neck and neck on quality (54.3 vs 52.9, within the ±6.4 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.
- MiniMax M3.1 Flash vs Mistral Large 4: which is cheaper, and will that change?
- MiniMax M3.1 Flash is cheaper today: $0.262 against $1.05 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is MiniMax M3.1 Flash or Mistral Large 4 better for coding?
- MiniMax M3.1 Flash scores higher in coding (55 vs 54 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1584 for MiniMax M3.1 Flash against 1565 for Mistral Large 4.
- Which is faster, MiniMax M3.1 Flash or Mistral Large 4?
- MiniMax M3.1 Flash streams faster (151 vs 97 output tokens per second, Artificial Analysis 7-day median).
- Is MiniMax M3.1 Flash or Mistral Large 4 better for agents and tool use?
- MiniMax M3.1 Flash scores higher in agentic tasks (55 vs 49 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is -2.7 for MiniMax M3.1 Flash against -5.4 for Mistral Large 4.
More questions (4)
- Which is better for long documents?
- They are level on long-context benchmarks (65 vs 65). Both take about 1M tokens: MiniMax M3.1 Flash 1,000,000, Mistral Large 4 1,048,576.
- Which has lower latency?
- Mistral Large 4 answers first: 40.9 s against 43.3 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.
- Do independent benchmarks agree on MiniMax M3.1 Flash vs Mistral Large 4?
- Across the 26 benchmarks both have, MiniMax M3.1 Flash leads 19, Mistral Large 4 leads 7. Every overall index that rates both puts MiniMax M3.1 Flash ahead.
- When was MiniMax M3.1 Flash released?
- MiniMax M3.1 Flash was released on 19 Oct 2026.