Llama 4 Maverick vs MiniMax M2.5
MiniMax M2.5 leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 22.8 to 9.3, and Llama 4 Maverick costs 1.2x less per output token ($1.00 vs $1.20 per million). Updated October 22, 2026; 55 benchmarks have a result for both.
Llama 4 Maverick or MiniMax M2.5: which to pick
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding.
Pick Llama 4 Maverick for output tokens 1.2x cheaper ($1.00 vs $1.20 per million) and a larger context window (524K against 205K tokens).
- Shared results
- 55
- Llama 4 Maverick only
- 30
- MiniMax M2.5 only
- 16
- Like-for-like categories
- 8 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
No call
Only MiniMax M2.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M2.5
MiniMax M2.5 leads, 22.8 against 9.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Llama 4 Maverick has a AA Agentic Index result, 0.6.
Directional only
Reasoning
GPQA Diamond
MiniMax M2.5
MiniMax M2.5 leads, 82.1% against 69.4%.
Same board, both measured
Math
AIME
MiniMax M2.5
MiniMax M2.5 leads, 88.8% against 25.2%.
Same board, both measured
Knowledge
MMLU Pro
MiniMax M2.5
MiniMax M2.5 leads, 80.1% against 79.4%.
Same board, both measured
Web design
Design Arena: websites
MiniMax M2.5
MiniMax M2.5 leads, 1222 against 871.
Same board, both measured
Long documents
Listed context window
Llama 4 Maverick
Llama 4 Maverick takes 524K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Maverick
Llama 4 Maverick $0.0008, MiniMax M2.5 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiniMax M2.5
Llama 4 Maverick $1.491, MiniMax M2.5 $0.62.
Published attempt cost and pass rate
At a glance
- Coding index
- Llama 4 Maverick not benchmarked, MiniMax M2.5 37.2 from 3 benchmarks.
- Widest category
- Agentic work, 77.5 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Llama 4 Maverick 17.8% against MiniMax M2.5 95.3%, 77.5 points apart on a 0 to 100 scale.
- Output price
- Llama 4 Maverick $1.00 against MiniMax M2.5 $1.20 per million output tokens, 1.2x apart.
- Context window
- Llama 4 Maverick takes 524K tokens, MiniMax M2.5 205K.
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 | Llama 4 Maverick | Bars | MiniMax M2.5 | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 8 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 9 | ||
| Web design | 0 | 6 | ||
| General | 1 | 18 | ||
| All shared boards | 2 | 53 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| Aider polyglot | 15.6% | Not measured | Only Llama 4 Maverick measured |
| SWE-bench Verified | 21.0% | 75.8% | MiniMax M2.5 |
| SWE-bench Multilingual | Not measured | 68.3% | Only MiniMax M2.5 measured |
| LMArena WebDev | Not measured | 1386 | Only MiniMax M2.5 measured |
| AA Coding Index | 16.3 | Not measured | Only Llama 4 Maverick measured |
| LiveCodeBench (Vals AI) | 47.3% | 79.2% | MiniMax M2.5 |
| SWE-bench Verified (Vals AI) | Not measured | 74.2% | Only MiniMax M2.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 14.8% | Only MiniMax M2.5 measured |
| LiveCodeBench (Artificial Analysis run) | 39.7% | Not measured | Only Llama 4 Maverick measured |
| SciCode | 31.7% | Not measured | Only Llama 4 Maverick measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.8% | 34.8% | MiniMax M2.5 |
| Terminal-Bench | Not measured | 42.7% | Only MiniMax M2.5 measured |
| WeirdML | 24.5% | Not measured | Only Llama 4 Maverick measured |
| ALE-Bench | 173.0 | 618.2 | MiniMax M2.5 |
| LMArena Text: coding | 1301 | 1380 | MiniMax M2.5 |
| LMArena Text: software and IT | 1299 | 1383 | MiniMax M2.5 |
| LMArena WebDev: React | Not measured | 1374 | Only MiniMax M2.5 measured |
| LMArena WebDev: HTML | Not measured | 1414 | Only MiniMax M2.5 measured |
| SWE Atlas: Codebase QnA | Not measured | 10.3% | Only MiniMax M2.5 measured |
| SWE Atlas: Refactoring | Not measured | 19.5% | Only MiniMax M2.5 measured |
| SWE Atlas: Test Writing | Not measured | 18.6% | Only MiniMax M2.5 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.3 | 22.8 | MiniMax M2.5 |
| Epoch Capabilities Index | 132.2 | 146.6 | MiniMax M2.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.6 | Not measured | Only Llama 4 Maverick measured |
| τ²-Bench Telecom | 17.8% | 95.3% | MiniMax M2.5 |
| Vending-Bench 2 | Not measured | -$23 | Only MiniMax M2.5 measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index18
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 69.4% | 82.1% | MiniMax M2.5 |
| MMMU Pro (Vals AI) | 71.7% | Not measured | Only Llama 4 Maverick measured |
| GPQA Diamond (Artificial Analysis run) | 67.1% | 84.8% | MiniMax M2.5 |
| Humanity's Last Exam (Artificial Analysis run) | 4.9% | 20.5% | MiniMax M2.5 |
| ARC-AGI | 4.4% | 63.7% | MiniMax M2.5 |
| ARC-AGI-2 | 0.0% | 4.9% | MiniMax M2.5 |
| SimpleBench | 27.7% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: hard prompts | 1281 | 1372 | MiniMax M2.5 |
| LMArena Text: expert | 1259 | 1378 | MiniMax M2.5 |
| LMArena Text: hard prompts in English | 1295 | 1384 | MiniMax M2.5 |
| LMArena Vision: diagrams | 1134 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: homework | 1164 | Not measured | Only Llama 4 Maverick measured |
| Kagi LLM Benchmark | 55.9% | 55.2% | Llama 4 Maverick |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| AIME | 25.2% | 88.8% | MiniMax M2.5 |
| MATH 500 (Vals AI) | 85.2% | Not measured | Only Llama 4 Maverick measured |
| MGSM (Vals AI) | 92.4% | Not measured | Only Llama 4 Maverick measured |
| AA Math Index | 19.3 | Not measured | Only Llama 4 Maverick measured |
| AIME 2025 (Artificial Analysis run) | 19.3% | Not measured | Only Llama 4 Maverick measured |
| ProofBench | Not measured | 4.0% | Only MiniMax M2.5 measured |
| LMArena Text: math | 1299 | 1378 | MiniMax M2.5 |
| LMArena Text: mathematical work | 1295 | 1378 | MiniMax M2.5 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 79.4% | 80.1% | MiniMax M2.5 |
| LegalBench (Vals AI) | 77.8% | 80.0% | MiniMax M2.5 |
| CaseLaw (Vals AI) | Not measured | 53.5% | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | 49.7% | 59.6% | MiniMax M2.5 |
| TaxEval (Vals AI) | 66.6% | 68.2% | MiniMax M2.5 |
| MortgageTax (Vals AI) | 58.5% | Not measured | Only Llama 4 Maverick measured |
| MedQA (Vals AI) | 43.3% | 92.5% | MiniMax M2.5 |
| MedCode (Vals AI) | 36.5% | Not measured | Only Llama 4 Maverick measured |
| MMLU Pro (Artificial Analysis run) | 80.9% | Not measured | Only Llama 4 Maverick measured |
| GeoBench | 52.0% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: science | 1288 | 1369 | MiniMax M2.5 |
| LMArena Text: medicine and healthcare | 1275 | 1357 | MiniMax M2.5 |
| LMArena Text: legal and government | 1286 | 1366 | MiniMax M2.5 |
| LMArena Text: business and finance | 1260 | 1356 | MiniMax M2.5 |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 871 | 1222 | MiniMax M2.5 |
| Design Arena: UI components | 897 | 1170 | MiniMax M2.5 |
| Design Arena: game dev | 837 | 1176 | MiniMax M2.5 |
| Design Arena: data viz | 882 | 1172 | MiniMax M2.5 |
| Design Arena: 3D | 900 | 1170 | MiniMax M2.5 |
| Design Arena: all code categories | 879 | 1207 | MiniMax M2.5 |
| Design Arena: SVG | Not measured | 1150 | Only MiniMax M2.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index118
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 35.7% | Not measured | Only Llama 4 Maverick measured |
| MedScribe (Vals AI) | 54.2% | Not measured | Only Llama 4 Maverick measured |
| IFBench | 43.0% | 71.6% | MiniMax M2.5 |
| Long context reasoning (AA-LCR) | 50.0% | 73.3% | MiniMax M2.5 |
| DTBench | 61.9% | Not measured | Only Llama 4 Maverick measured |
| LMCA | 15.9% | Not measured | Only Llama 4 Maverick measured |
| Fiction.LiveBench | 46.2% | Not measured | Only Llama 4 Maverick measured |
| Creative writing (Lech Mazur) | 62.0% | Not measured | Only Llama 4 Maverick measured |
| CL-bench | Not measured | 11.4% | Only MiniMax M2.5 measured |
| CL-bench Life | Not measured | 6.3% | Only MiniMax M2.5 measured |
| LMArena Text | 1287 | 1359 | MiniMax M2.5 |
| LMArena Text: instruction following | 1267 | 1353 | MiniMax M2.5 |
| LMArena Text: creative writing | 1266 | 1331 | MiniMax M2.5 |
| LMArena Vision | 1142 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: English | 1303 | 1380 | MiniMax M2.5 |
| LMArena Text: non-English | 1269 | 1338 | MiniMax M2.5 |
| LMArena Text: Chinese | 1277 | 1393 | MiniMax M2.5 |
| LMArena Text: German | 1291 | 1361 | MiniMax M2.5 |
| LMArena Text: Japanese | 1206 | 1171 | Llama 4 Maverick |
| LMArena Text: Korean | 1203 | 1233 | MiniMax M2.5 |
| LMArena Text: French | 1259 | 1363 | MiniMax M2.5 |
| LMArena Text: Spanish | 1293 | 1353 | MiniMax M2.5 |
| LMArena Text: Russian | 1286 | 1359 | MiniMax M2.5 |
| LMArena Text: Polish | 1275 | 1334 | MiniMax M2.5 |
| LMArena Text: multi-turn | 1289 | 1364 | MiniMax M2.5 |
| LMArena Text: longer queries | 1280 | 1366 | MiniMax M2.5 |
| LMArena Text: writing and language | 1277 | 1345 | MiniMax M2.5 |
| LMArena Text: entertainment and media | 1250 | 1329 | MiniMax M2.5 |
| LMArena Vision: English | 1150 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: Chinese | 1141 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: reading text | 1143 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: humor | 1100 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: creative writing | 1099 | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Llama 4 Maverick | MiniMax M2.5 | 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
Llama 4 Maverick 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 | Meta Llama 4 Maverick | MiniMax M2.5 |
|---|---|---|
| Maker | Meta Llama | MiniMax |
| Weights | Open weights | Open weights |
| Released | April 5, 2025 | February 12, 2026 |
| Context window | 524K | 205K |
| Input $/Mtok | $0.35 | $0.30 |
| Output $/Mtok | $1.00 | $1.20 |
| Coding index | Not benchmarked | 37.2 |
| Independent measurements behind it | 0 | 3 |
| Cost per solved task | $1.491 | $0.62 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Llama 4 Maverick better than MiniMax M2.5 for coding?
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding. Pick Llama 4 Maverick for output tokens 1.2x cheaper ($1.00 vs $1.20 per million) and a larger context window (524K against 205K tokens).
Which is cheaper, Llama 4 Maverick or MiniMax M2.5?
Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens; MiniMax M2.5 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Llama 4 Maverick costs $1.491 and MiniMax M2.5 $0.62.
Which has the bigger context window, Llama 4 Maverick or MiniMax M2.5?
Llama 4 Maverick, with 524K tokens against 205K.
How many benchmarks is the Llama 4 Maverick vs MiniMax M2.5 comparison based on?
55 benchmarks have a result for both models as of October 22, 2026. Llama 4 Maverick's coding index rests on 0 independent benchmarks and MiniMax M2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.