Claude Sonnet 4.6 vs MiniMax M2.5
Claude Sonnet 4.6 leads MiniMax M2.5 on coding, 57.3 to 37.2 on the Vibe Coding Index, and MiniMax M2.5 costs 12.5x less per output token ($1.20 vs $15.00 per million). Updated October 22, 2026; 65 benchmarks have a result for both.
Claude Sonnet 4.6 or MiniMax M2.5: which to pick
Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 37.2 for MiniMax M2.5.
Pick MiniMax M2.5 for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.62 against $1.68).
- Shared results
- 65
- Claude Sonnet 4.6 only
- 58
- MiniMax M2.5 only
- 6
- 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
Claude Sonnet 4.6
Claude Sonnet 4.6 scores 57.3 against 37.2.
5 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 30.1 against 22.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Sonnet 4.6 has a AA Agentic Index result, 31.8.
Directional only
Reasoning
GPQA Diamond
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 85.6% against 82.1%.
Same board, both measured
Math
AIME
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 92.3% against 88.8%.
Same board, both measured
Knowledge
MMLU Pro
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 87.3% against 80.1%.
Same board, both measured
Web design
Design Arena: websites
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 1284 against 1222.
Same board, both measured
Long documents
Listed context window
Claude Sonnet 4.6
Claude Sonnet 4.6 takes 1M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
Claude Sonnet 4.6 $0.011, MiniMax M2.5 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiniMax M2.5
Claude Sonnet 4.6 $1.68, MiniMax M2.5 $0.62.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Sonnet 4.6 57.3 from 5 benchmarks, MiniMax M2.5 37.2 from 3 benchmarks.
- Widest category
- Agentic work, 30.4 points apart on average over 2 shared benchmarks.
- Widest single gap
- ARC-AGI-2: Claude Sonnet 4.6 60.4% against MiniMax M2.5 4.9%, 55.6 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.6 $15.00 against MiniMax M2.5 $1.20 per million output tokens, 12.5x apart.
- Context window
- Claude Sonnet 4.6 takes 1M 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 | Claude Sonnet 4.6 | Bars | MiniMax M2.5 | Ties |
|---|---|---|---|---|
| Coding | 13 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 8 | 0 | ||
| Math | 4 | 0 | ||
| Knowledge | 9 | 1 | ||
| Web design | 7 | 0 | ||
| General | 18 | 1 | ||
| All shared boards | 62 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index130
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 75.8% | Only MiniMax M2.5 measured |
| SWE-bench Multilingual | Not measured | 68.3% | Only MiniMax M2.5 measured |
| LiveBench coding | 66.6% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena WebDev | 1523 | 1386 | Claude Sonnet 4.6 |
| AA Coding Index | 63.0 | Not measured | Only Claude Sonnet 4.6 measured |
| LiveCodeBench (Vals AI) | 82.1% | 79.2% | Claude Sonnet 4.6 |
| SWE-bench Verified (Vals AI) | 77.4% | 74.2% | Claude Sonnet 4.6 |
| Vibe Code Bench (Vals AI) | 55.8% | 14.8% | Claude Sonnet 4.6 |
| Code migration (Vals AI) | 39.9% | Not measured | Only Claude Sonnet 4.6 measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench 2.1 (Vals AI) | 57.3% | Not measured | Only Claude Sonnet 4.6 measured |
| SkillsBench (Vals AI) | 49.0% | Not measured | Only Claude Sonnet 4.6 measured |
| SciCode | 50.1% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 53.0% | 34.8% | Claude Sonnet 4.6 |
| Terminal-Bench | 53.4% | 42.7% | Claude Sonnet 4.6 |
| FrontierCode | 24.3% | Not measured | Only Claude Sonnet 4.6 measured |
| WeirdML | 66.1% | Not measured | Only Claude Sonnet 4.6 measured |
| ALE-Bench | Not measured | 618.2 | Only MiniMax M2.5 measured |
| LMArena Text: coding | 1503 | 1380 | Claude Sonnet 4.6 |
| LMArena Text: software and IT | 1491 | 1383 | Claude Sonnet 4.6 |
| LMArena WebDev: React | 1512 | 1374 | Claude Sonnet 4.6 |
| LMArena WebDev: HTML | 1527 | 1414 | Claude Sonnet 4.6 |
| LMArena WebDev: from an image | 1529 | Not measured | Only Claude Sonnet 4.6 measured |
| SWE Atlas: Codebase QnA | 31.2% | 10.3% | Claude Sonnet 4.6 |
| SWE Atlas: Refactoring | 32.2% | 19.5% | Claude Sonnet 4.6 |
| SWE Atlas: Test Writing | 31.8% | 18.6% | Claude Sonnet 4.6 |
| Neither model has a result on the other 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.1 | 22.8 | Claude Sonnet 4.6 |
| Epoch Capabilities Index | 152.8 | 146.6 | Claude Sonnet 4.6 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 31.8 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building web apps | 1190 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building full-stack apps | 1213 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building mobile apps | 1211 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building Android apps | 1196 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building Godot games | 1226 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building games | 1177 | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench research | 63.6% | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench browser | 68.0% | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench long agentic | 23.1% | Not measured | Only Claude Sonnet 4.6 measured |
| Finance Agent (Vals AI) | 51.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Tax Agent Bench (Vals AI) | 25.8% | Not measured | Only Claude Sonnet 4.6 measured |
| Legal Research Bench (Vals AI) | 38.5% | Not measured | Only Claude Sonnet 4.6 measured |
| Excel Modeling Benchmark (Vals AI) | 60.2% | Not measured | Only Claude Sonnet 4.6 measured |
| τ²-Bench Telecom | 79.5% | 95.3% | MiniMax M2.5 |
| APEX-Agents | 43.0% | Not measured | Only Claude Sonnet 4.6 measured |
| OSWorld 2.0 | 9.3% | Not measured | Only Claude Sonnet 4.6 measured |
| DeepResearch Bench | 54.9% | Not measured | Only Claude Sonnet 4.6 measured |
| OSWorld | 72.1% | Not measured | Only Claude Sonnet 4.6 measured |
| Vending-Bench 2 | $7,204 | -$23 | Claude Sonnet 4.6 |
| MCP Atlas | 69.5% | Not measured | Only Claude Sonnet 4.6 measured |
| Neither model has a result on the other 21 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | 82.1% | Claude Sonnet 4.6 |
| LiveBench reasoning | 86.4% | Not measured | Only Claude Sonnet 4.6 measured |
| MMMU Pro (Vals AI) | 83.6% | Not measured | Only Claude Sonnet 4.6 measured |
| GPQA Diamond (Artificial Analysis run) | 87.5% | 84.8% | Claude Sonnet 4.6 |
| Humanity's Last Exam (Artificial Analysis run) | 33.6% | 20.5% | Claude Sonnet 4.6 |
| GPQA Diamond (Epoch AI run) | 87.4% | Not measured | Only Claude Sonnet 4.6 measured |
| ARC-AGI | 86.5% | 63.7% | Claude Sonnet 4.6 |
| ARC-AGI-2 | 60.4% | 4.9% | Claude Sonnet 4.6 |
| Chess puzzles | 23.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Mystery game puzzles | 16.0% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: hard prompts | 1485 | 1372 | Claude Sonnet 4.6 |
| LMArena Text: expert | 1500 | 1378 | Claude Sonnet 4.6 |
| LMArena Text: hard prompts in English | 1493 | 1384 | Claude Sonnet 4.6 |
| LMArena Vision: diagrams | 1306 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: homework | 1311 | Not measured | Only Claude Sonnet 4.6 measured |
| Kagi LLM Benchmark | Not measured | 55.2% | 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 index40
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AIME | 92.3% | 88.8% | Claude Sonnet 4.6 |
| OTIS Mock AIME | 85.8% | Not measured | Only Claude Sonnet 4.6 measured |
| ProofBench | 45.0% | 4.0% | Claude Sonnet 4.6 |
| LMArena Text: math | 1462 | 1378 | Claude Sonnet 4.6 |
| LMArena Text: mathematical work | 1483 | 1378 | Claude Sonnet 4.6 |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 80.1% | Claude Sonnet 4.6 |
| LegalBench (Vals AI) | 82.1% | 80.0% | Claude Sonnet 4.6 |
| CaseLaw (Vals AI) | 64.0% | 53.5% | Claude Sonnet 4.6 |
| CorpFin (Vals AI) | 65.3% | 59.6% | Claude Sonnet 4.6 |
| TaxEval (Vals AI) | 77.1% | 68.2% | Claude Sonnet 4.6 |
| MortgageTax (Vals AI) | 67.7% | Not measured | Only Claude Sonnet 4.6 measured |
| MedQA (Vals AI) | 92.1% | 92.5% | MiniMax M2.5 |
| SimpleQA Verified | 35.5% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: science | 1474 | 1369 | Claude Sonnet 4.6 |
| LMArena Text: medicine and healthcare | 1451 | 1357 | Claude Sonnet 4.6 |
| LMArena Text: legal and government | 1470 | 1366 | Claude Sonnet 4.6 |
| LMArena Text: business and finance | 1464 | 1356 | Claude Sonnet 4.6 |
| FACTS Benchmark Suite | 37.0% | Not measured | Only Claude Sonnet 4.6 measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1284 | 1222 | Claude Sonnet 4.6 |
| Design Arena: UI components | 1269 | 1170 | Claude Sonnet 4.6 |
| Design Arena: game dev | 1258 | 1176 | Claude Sonnet 4.6 |
| Design Arena: data viz | 1278 | 1172 | Claude Sonnet 4.6 |
| Design Arena: 3D | 1234 | 1170 | Claude Sonnet 4.6 |
| Design Arena: all code categories | 1275 | 1207 | Claude Sonnet 4.6 |
| Design Arena: SVG | 1196 | 1150 | Claude Sonnet 4.6 |
| Design Arena: ASCII art | 1235 | Not measured | Only Claude Sonnet 4.6 measured |
| LiveBench design | 71.8% | Not measured | Only Claude Sonnet 4.6 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index181
| Benchmark | Claude Sonnet 4.6 | MiniMax M2.5 | Leader |
|---|---|---|---|
| LiveBench data analysis | 76.1% | Not measured | Only Claude Sonnet 4.6 measured |
| Public Benefits Bench (Vals AI) | 62.5% | Not measured | Only Claude Sonnet 4.6 measured |
| SAGE (Vals AI) | 46.6% | Not measured | Only Claude Sonnet 4.6 measured |
| Vals Multimodal Index | 60.6% | Not measured | Only Claude Sonnet 4.6 measured |
| IFBench | 56.6% | 71.6% | MiniMax M2.5 |
| Long context reasoning (AA-LCR) | 80.0% | 73.3% | Claude Sonnet 4.6 |
| DTBench | 89.9% | Not measured | Only Claude Sonnet 4.6 measured |
| LMCA | 46.5% | Not measured | Only Claude Sonnet 4.6 measured |
| CL-bench | Not measured | 11.4% | Only MiniMax M2.5 measured |
| ExploitBench | 23.6% | Not measured | Only Claude Sonnet 4.6 measured |
| CL-bench Life | Not measured | 6.3% | Only MiniMax M2.5 measured |
| LMArena Text | 1458 | 1359 | Claude Sonnet 4.6 |
| LMArena Text: instruction following | 1476 | 1353 | Claude Sonnet 4.6 |
| LMArena Text: creative writing | 1435 | 1331 | Claude Sonnet 4.6 |
| LMArena Vision | 1283 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: English | 1472 | 1380 | Claude Sonnet 4.6 |
| LMArena Text: non-English | 1440 | 1338 | Claude Sonnet 4.6 |
| LMArena Text: Chinese | 1491 | 1393 | Claude Sonnet 4.6 |
| LMArena Text: German | 1428 | 1361 | Claude Sonnet 4.6 |
| LMArena Text: Japanese | 1420 | 1171 | Claude Sonnet 4.6 |
| LMArena Text: Korean | 1410 | 1233 | Claude Sonnet 4.6 |
| LMArena Text: French | 1465 | 1363 | Claude Sonnet 4.6 |
| LMArena Text: Spanish | 1464 | 1353 | Claude Sonnet 4.6 |
| LMArena Text: Russian | 1440 | 1359 | Claude Sonnet 4.6 |
| LMArena Text: Polish | 1443 | 1334 | Claude Sonnet 4.6 |
| LMArena Text: multi-turn | 1464 | 1364 | Claude Sonnet 4.6 |
| LMArena Text: longer queries | 1479 | 1366 | Claude Sonnet 4.6 |
| LMArena Text: writing and language | 1444 | 1345 | Claude Sonnet 4.6 |
| LMArena Text: entertainment and media | 1431 | 1329 | Claude Sonnet 4.6 |
| LMArena Vision: English | 1298 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: Chinese | 1307 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: reading text | 1296 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: humor | 1248 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: recognizing things | 1195 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Vision: creative writing | 1272 | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Document | 1482 | Not measured | Only Claude Sonnet 4.6 measured |
| EQ-Bench 4 | 1207 | Not measured | Only Claude Sonnet 4.6 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.6 | 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
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 | Anthropic Claude Sonnet 4.6 | MiniMax M2.5 |
|---|---|---|
| Maker | Anthropic | MiniMax |
| Weights | No public weights listed | Open weights |
| Released | February 17, 2026 | February 12, 2026 |
| Context window | 1M | 205K |
| Input $/Mtok | $3.00 | $0.30 |
| Output $/Mtok | $15.00 | $1.20 |
| Coding index | 57.3 | 37.2 |
| Independent measurements behind it | 5 | 3 |
| Cost per solved task | $1.68 | $0.62 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.6 better than MiniMax M2.5 for coding?
Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 37.2 for MiniMax M2.5. Pick MiniMax M2.5 for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.62 against $1.68).
Which is cheaper, Claude Sonnet 4.6 or MiniMax M2.5?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; MiniMax M2.5 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and MiniMax M2.5 $0.62.
Which has the bigger context window, Claude Sonnet 4.6 or MiniMax M2.5?
Claude Sonnet 4.6, with 1M tokens against 205K.
How many benchmarks is the Claude Sonnet 4.6 vs MiniMax M2.5 comparison based on?
65 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.6's coding index rests on 5 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.