MiniMax M2.5 vs Mistral Large 4
Mistral Large 4 leads MiniMax M2.5 on coding, 56.4 to 37.2 on the Vibe Coding Index, and MiniMax M2.5 costs 3.5x less per output token ($1.20 vs $4.18 per million). Updated October 22, 2026; 42 benchmarks have a result for both.
MiniMax M2.5 or Mistral Large 4: which to pick
Pick Mistral Large 4 for coding: it scores 56.4 on the Vibe Coding Index against 37.2 for MiniMax M2.5.
Pick MiniMax M2.5 for output tokens 3.5x cheaper ($1.20 vs $4.18 per million).
- Shared results
- 42
- MiniMax M2.5 only
- 26
- Mistral Large 4 only
- 39
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Mistral Large 4
Mistral Large 4 scores 56.4 against 37.2.
3 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Mistral Large 4
Mistral Large 4 leads, 38.4 against 22.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only MiniMax M2.5 has a GPQA Diamond result, 82.1%.
Directional only
Math
AIME
No call
Only MiniMax M2.5 has a AIME result, 88.8%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M2.5 has a MMLU Pro result, 80.1%.
Directional only
Web design
Design Arena: websites
Mistral Large 4
Mistral Large 4 leads, 1258 against 1222.
Same board, both measured
Long documents
Listed context window
Mistral Large 4
Mistral Large 4 takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
MiniMax M2.5 $0.0009, Mistral Large 4 $0.0034 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.5 has the number, $0.62.
Directional only
At a glance
- Coding index
- MiniMax M2.5 37.2 from 3 benchmarks, Mistral Large 4 56.4 from 5 benchmarks.
- Widest category
- Coding, 25.6 points apart on average over 7 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): MiniMax M2.5 14.8% against Mistral Large 4 78.4%, 63.6 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $1.20 against Mistral Large 4 $4.18 per million output tokens, 3.5x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, Mistral Large 4 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | MiniMax M2.5 | Bars | Mistral Large 4 | Ties |
|---|---|---|---|---|
| Coding | 0 | 7 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 7 | ||
| General | 0 | 15 | ||
| All shared boards | 0 | 42 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| SWE-bench Verified | 75.8% | Not measured | Only MiniMax M2.5 measured |
| SWE-bench Multilingual | 68.3% | Not measured | Only MiniMax M2.5 measured |
| LiveBench coding | Not measured | 60.0% | Only Mistral Large 4 measured |
| LMArena WebDev | 1386 | 1543 | Mistral Large 4 |
| LiveCodeBench (Vals AI) | 79.2% | Not measured | Only MiniMax M2.5 measured |
| SWE-bench Verified (Vals AI) | 74.2% | Not measured | Only MiniMax M2.5 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 27.8% | Only Mistral Large 4 measured |
| Vibe Code Bench (Vals AI) | 14.8% | 78.4% | Mistral Large 4 |
| Code migration (Vals AI) | Not measured | 30.6% | Only Mistral Large 4 measured |
| IOI (Vals AI) | Not measured | 45.3% | Only Mistral Large 4 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 33.1% | Only Mistral Large 4 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 14.3% | Only Mistral Large 4 measured |
| SciCode | Not measured | 54.2% | Only Mistral Large 4 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | Not measured | Only MiniMax M2.5 measured |
| Terminal-Bench | 42.7% | Not measured | Only MiniMax M2.5 measured |
| FrontierCode | Not measured | 39.4% | Only Mistral Large 4 measured |
| ALE-Bench | 618.2 | 1213.2 | Mistral Large 4 |
| LMArena Text: coding | 1380 | 1478 | Mistral Large 4 |
| LMArena Text: software and IT | 1383 | 1467 | Mistral Large 4 |
| LMArena WebDev: React | 1374 | 1559 | Mistral Large 4 |
| LMArena WebDev: HTML | 1414 | 1487 | Mistral Large 4 |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 38.4 | Mistral Large 4 |
| Epoch Capabilities Index | 146.6 | 150.0 | Mistral Large 4 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench research | Not measured | 28.1% | Only Mistral Large 4 measured |
| LiveBench browser | Not measured | 8.0% | Only Mistral Large 4 measured |
| LiveBench long agentic | Not measured | 11.8% | Only Mistral Large 4 measured |
| Finance Agent (Vals AI) | Not measured | 54.7% | Only Mistral Large 4 measured |
| Tax Agent Bench (Vals AI) | Not measured | 30.4% | Only Mistral Large 4 measured |
| Legal Research Bench (Vals AI) | Not measured | 31.7% | Only Mistral Large 4 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 17.5% | Only Mistral Large 4 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 56.2% | Only Mistral Large 4 measured |
| BioMysteryBench (Vals AI) | Not measured | 67.0% | Only Mistral Large 4 measured |
| τ²-Bench Telecom | 95.3% | Not measured | Only MiniMax M2.5 measured |
| Vending-Bench 2 | -$23 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | Not measured | Only MiniMax M2.5 measured |
| LiveBench reasoning | Not measured | 83.9% | Only Mistral Large 4 measured |
| MysteryMechanism (Vals AI) | Not measured | 12.2% | Only Mistral Large 4 measured |
| GPQA Diamond (Artificial Analysis run) | 84.8% | Not measured | Only MiniMax M2.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | 35.0% | Mistral Large 4 |
| GPQA Diamond (Epoch AI run) | Not measured | 88.1% | Only Mistral Large 4 measured |
| ARC-AGI | 63.7% | Not measured | Only MiniMax M2.5 measured |
| ARC-AGI-2 | 4.9% | Not measured | Only MiniMax M2.5 measured |
| Chess puzzles | Not measured | 33.0% | Only Mistral Large 4 measured |
| Mystery game puzzles | Not measured | 17.0% | Only Mistral Large 4 measured |
| LMArena Text: hard prompts | 1372 | 1444 | Mistral Large 4 |
| LMArena Text: expert | 1378 | 1444 | Mistral Large 4 |
| LMArena Text: hard prompts in English | 1384 | 1442 | Mistral Large 4 |
| LMArena Vision: diagrams | Not measured | 1288 | Only Mistral Large 4 measured |
| Kagi LLM Benchmark | 55.2% | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only MiniMax M2.5 measured |
| OTIS Mock AIME | Not measured | 98.3% | Only Mistral Large 4 measured |
| FrontierMath, tiers 1 to 3 | Not measured | 58.6% | Only Mistral Large 4 measured |
| FrontierMath, tier 4 | Not measured | 26.8% | Only Mistral Large 4 measured |
| ProofBench | 4.0% | 10.0% | Mistral Large 4 |
| LMArena Text: math | 1378 | 1469 | Mistral Large 4 |
| LMArena Text: mathematical work | 1378 | 1462 | Mistral Large 4 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| MMLU Pro | 80.1% | Not measured | Only MiniMax M2.5 measured |
| LegalBench (Vals AI) | 80.0% | Not measured | Only MiniMax M2.5 measured |
| CaseLaw (Vals AI) | 53.5% | Not measured | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | 59.6% | Not measured | Only MiniMax M2.5 measured |
| TaxEval (Vals AI) | 68.2% | Not measured | Only MiniMax M2.5 measured |
| MedQA (Vals AI) | 92.5% | Not measured | Only MiniMax M2.5 measured |
| MedCode (Vals AI) | Not measured | 40.7% | Only Mistral Large 4 measured |
| SimpleQA Verified | Not measured | 20.0% | Only Mistral Large 4 measured |
| LMArena Text: science | 1369 | 1448 | Mistral Large 4 |
| LMArena Text: medicine and healthcare | 1357 | 1433 | Mistral Large 4 |
| LMArena Text: legal and government | 1366 | 1425 | Mistral Large 4 |
| LMArena Text: business and finance | 1356 | 1439 | Mistral Large 4 |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | 1258 | Mistral Large 4 |
| Design Arena: UI components | 1170 | 1273 | Mistral Large 4 |
| Design Arena: game dev | 1176 | 1225 | Mistral Large 4 |
| Design Arena: data viz | 1172 | 1275 | Mistral Large 4 |
| Design Arena: 3D | 1170 | 1252 | Mistral Large 4 |
| Design Arena: all code categories | 1207 | 1259 | Mistral Large 4 |
| Design Arena: SVG | 1150 | 1232 | Mistral Large 4 |
| Design Arena: ASCII art | Not measured | 1202 | Only Mistral Large 4 measured |
| LiveBench design | Not measured | 65.6% | Only Mistral Large 4 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index015
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 76.5% | Only Mistral Large 4 measured |
| MedScribe (Vals AI) | Not measured | 80.4% | Only Mistral Large 4 measured |
| IFBench | 71.6% | Not measured | Only MiniMax M2.5 measured |
| Long context reasoning (AA-LCR) | 73.3% | 81.3% | Mistral Large 4 |
| DTBench | Not measured | 88.2% | Only Mistral Large 4 measured |
| LMCA | Not measured | 35.8% | Only Mistral Large 4 measured |
| CL-bench | 11.4% | Not measured | Only MiniMax M2.5 measured |
| Surface Evolver Bench | Not measured | 28.1% | Only Mistral Large 4 measured |
| Furniture assembly | Not measured | 20.8% | Only Mistral Large 4 measured |
| CL-bench Life | 6.3% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text | 1359 | 1431 | Mistral Large 4 |
| LMArena Text: instruction following | 1353 | 1422 | Mistral Large 4 |
| LMArena Text: creative writing | 1331 | 1363 | Mistral Large 4 |
| LMArena Vision | Not measured | 1272 | Only Mistral Large 4 measured |
| LMArena Text: English | 1380 | 1433 | Mistral Large 4 |
| LMArena Text: non-English | 1338 | 1422 | Mistral Large 4 |
| LMArena Text: Chinese | 1393 | 1492 | Mistral Large 4 |
| LMArena Text: German | 1361 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Japanese | 1171 | 1415 | Mistral Large 4 |
| LMArena Text: Korean | 1233 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: French | 1363 | 1492 | Mistral Large 4 |
| LMArena Text: Spanish | 1353 | 1455 | Mistral Large 4 |
| LMArena Text: Russian | 1359 | 1417 | Mistral Large 4 |
| LMArena Text: Polish | 1334 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: multi-turn | 1364 | 1435 | Mistral Large 4 |
| LMArena Text: longer queries | 1366 | 1428 | Mistral Large 4 |
| LMArena Text: writing and language | 1345 | 1386 | Mistral Large 4 |
| LMArena Text: entertainment and media | 1329 | 1378 | Mistral Large 4 |
| LMArena Vision: English | Not measured | 1283 | Only Mistral Large 4 measured |
| LMArena Vision: reading text | Not measured | 1284 | Only Mistral Large 4 measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | Mistral Large 4 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
MiniMax M2.5 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.5 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | MiniMax M2.5 | Mistral Large 4 |
|---|---|---|
| Maker | MiniMax | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | February 12, 2026 | October 6, 2026 |
| Context window | 205K | 1.05M |
| Input $/Mtok | $0.30 | $1.36 |
| Output $/Mtok | $1.20 | $4.18 |
| Coding index | 37.2 | 56.4 |
| Independent measurements behind it | 3 | 5 |
| Cost per solved task | $0.62 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Mistral Large 4 for coding?
Pick Mistral Large 4 for coding: it scores 56.4 on the Vibe Coding Index against 37.2 for MiniMax M2.5. Pick MiniMax M2.5 for output tokens 3.5x cheaper ($1.20 vs $4.18 per million).
Which is cheaper, MiniMax M2.5 or Mistral Large 4?
MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Mistral Large 4 costs $1.36 and $4.18. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, MiniMax M2.5 or Mistral Large 4?
Mistral Large 4, with 1.05M tokens against 205K.
How many benchmarks is the MiniMax M2.5 vs Mistral Large 4 comparison based on?
42 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Mistral Large 4's on 5. Where only one model has a result, the page says so instead of naming a winner.