Claude Sonnet 4.6 vs MiniMax M3
Claude Sonnet 4.6 leads MiniMax M3 on coding, 57.3 to 39.2 on the Vibe Coding Index, and MiniMax M3 costs 12.5x less per output token ($1.20 vs $15.00 per million). Updated October 22, 2026; 104 benchmarks have a result for both.
Claude Sonnet 4.6 or MiniMax M3: which to pick
Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 5 benchmarks against 6.
Pick MiniMax M3 for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.56 against $1.68).
- Shared results
- 104
- Claude Sonnet 4.6 only
- 14
- MiniMax M3 only
- 12
- 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 39.2.
5 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 30.1 against 29.2.
Same board, both measured
Agentic work
AA Agentic Index
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 31.8 against 29.5.
Same board, both measured
Reasoning
GPQA Diamond
MiniMax M3
MiniMax M3 leads, 92.7% against 85.6%.
Same board, both measured
Math
AIME
No call
Only Claude Sonnet 4.6 has a AIME result, 92.3%.
Directional only
Knowledge
MMLU Pro
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 87.3% against 84.2%.
Same board, both measured
Web design
Design Arena: websites
Claude Sonnet 4.6
Claude Sonnet 4.6 leads, 1284 against 1257.
Same board, both measured
Long documents
Listed context window
MiniMax M3
MiniMax M3 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M3
Claude Sonnet 4.6 $0.011, MiniMax M3 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiniMax M3
Claude Sonnet 4.6 $1.68, MiniMax M3 $0.56.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Sonnet 4.6 57.3 from 5 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
- Widest category
- Math, 13.2 points apart on average over 4 shared benchmarks.
- Widest single gap
- LiveBench browser: Claude Sonnet 4.6 68.0% against MiniMax M3 8.0%, 60.0 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.6 $15.00 against MiniMax M3 $1.20 per million output tokens, 12.5x apart.
- Context window
- Claude Sonnet 4.6 takes 1M tokens, MiniMax M3 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 | Claude Sonnet 4.6 | Bars | MiniMax M3 | Ties |
|---|---|---|---|---|
| Coding | 14 | 3 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 14 | 3 | ||
| Reasoning | 9 | 4 | ||
| Math | 4 | 0 | ||
| Knowledge | 6 | 3 | ||
| Web design | 9 | 0 | ||
| General | 25 | 8 | ||
| All shared boards | 83 | 21 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index143
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| LiveBench coding | 66.6% | 70.9% | MiniMax M3 |
| LMArena WebDev | 1523 | 1482 | Claude Sonnet 4.6 |
| AA Coding Index | 63.0 | 58.6 | Claude Sonnet 4.6 |
| LiveCodeBench (Vals AI) | 82.1% | 82.2% | MiniMax M3 |
| SWE-bench Verified (Vals AI) | 77.4% | 75.0% | Claude Sonnet 4.6 |
| Terminal-Bench 4 (Vals AI) | Not measured | 1.0% | Only MiniMax M3 measured |
| Vibe Code Bench (Vals AI) | 55.8% | 47.6% | Claude Sonnet 4.6 |
| Code migration (Vals AI) | 39.9% | 19.9% | Claude Sonnet 4.6 |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only Claude Sonnet 4.6 measured |
| Terminal-Bench 2.1 (Vals AI) | 57.3% | 53.6% | Claude Sonnet 4.6 |
| SWE-bench Multimodal (Vals AI) | Not measured | 33.3% | Only MiniMax M3 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 9.2% | Only MiniMax M3 measured |
| SkillsBench (Vals AI) | 49.0% | 51.5% | MiniMax M3 |
| CyberBench (Vals AI) | Not measured | 65.0% | Only MiniMax M3 measured |
| SciCode | 50.1% | 47.1% | Claude Sonnet 4.6 |
| Terminal-Bench Hard (Artificial Analysis run) | 53.0% | 42.4% | Claude Sonnet 4.6 |
| Terminal-Bench | 53.4% | Not measured | Only Claude Sonnet 4.6 measured |
| FrontierCode | 24.3% | 14.7% | Claude Sonnet 4.6 |
| WeirdML | 66.1% | Not measured | Only Claude Sonnet 4.6 measured |
| ALE-Bench | Not measured | 640.0 | Only MiniMax M3 measured |
| LMArena Text: coding | 1503 | 1470 | Claude Sonnet 4.6 |
| LMArena Text: software and IT | 1491 | 1466 | Claude Sonnet 4.6 |
| LMArena WebDev: React | 1512 | 1478 | Claude Sonnet 4.6 |
| LMArena WebDev: HTML | 1527 | 1455 | Claude Sonnet 4.6 |
| LMArena WebDev: from an image | 1529 | 1470 | Claude Sonnet 4.6 |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.1 | 29.2 | Claude Sonnet 4.6 |
| Epoch Capabilities Index | 152.8 | 146.9 | Claude Sonnet 4.6 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index143
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| AA Agentic Index | 31.8 | 29.5 | Claude Sonnet 4.6 |
| Design Arena: agents building web apps | 1190 | 1200 | MiniMax M3 |
| Design Arena: agents building full-stack apps | 1213 | 1197 | Claude Sonnet 4.6 |
| Design Arena: agents building mobile apps | 1212 | 1169 | Claude Sonnet 4.6 |
| Design Arena: agents building Android apps | 1197 | 1159 | Claude Sonnet 4.6 |
| Design Arena: agents building Godot games | 1226 | Not measured | Only Claude Sonnet 4.6 measured |
| Design Arena: agents building games | 1177 | 1158 | Claude Sonnet 4.6 |
| Design Arena: HTML slides | Not measured | 1130 | Only MiniMax M3 measured |
| Design Arena: PowerPoint slides | Not measured | 1181 | Only MiniMax M3 measured |
| Design Arena: spreadsheets | Not measured | 1028 | Only MiniMax M3 measured |
| LiveBench research | 63.6% | 68.0% | MiniMax M3 |
| LiveBench browser | 68.0% | 8.0% | Claude Sonnet 4.6 |
| LiveBench long agentic | 23.1% | 12.4% | Claude Sonnet 4.6 |
| Finance Agent (Vals AI) | 51.0% | 48.3% | Claude Sonnet 4.6 |
| Tax Agent Bench (Vals AI) | 25.8% | 20.6% | Claude Sonnet 4.6 |
| Legal Research Bench (Vals AI) | 38.5% | 29.8% | Claude Sonnet 4.6 |
| Excel Modeling Benchmark (Vals AI) | 60.2% | 47.8% | Claude Sonnet 4.6 |
| τ²-Bench Telecom | 79.5% | 88.9% | MiniMax M3 |
| APEX-Agents | 43.0% | 37.7% | Claude Sonnet 4.6 |
| OSWorld 2.0 | 9.3% | 4.6% | Claude Sonnet 4.6 |
| 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 | $2,158 | Claude Sonnet 4.6 |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index94
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | 92.7% | MiniMax M3 |
| LiveBench reasoning | 86.4% | 74.5% | Claude Sonnet 4.6 |
| MMMU Pro (Vals AI) | 83.6% | 81.2% | Claude Sonnet 4.6 |
| GPQA Diamond (Artificial Analysis run) | 87.5% | 92.9% | MiniMax M3 |
| Humanity's Last Exam (Artificial Analysis run) | 33.6% | 39.0% | MiniMax M3 |
| GPQA Diamond (Epoch AI run) | 87.4% | 90.9% | MiniMax M3 |
| ARC-AGI | 86.5% | Not measured | Only Claude Sonnet 4.6 measured |
| ARC-AGI-2 | 60.4% | Not measured | Only Claude Sonnet 4.6 measured |
| SimpleBench | Not measured | 45.8% | Only MiniMax M3 measured |
| Chess puzzles | 23.0% | 13.0% | Claude Sonnet 4.6 |
| Mystery game puzzles | 16.0% | 8.0% | Claude Sonnet 4.6 |
| LMArena Text: hard prompts | 1485 | 1447 | Claude Sonnet 4.6 |
| LMArena Text: expert | 1500 | 1461 | Claude Sonnet 4.6 |
| LMArena Text: hard prompts in English | 1493 | 1455 | Claude Sonnet 4.6 |
| LMArena Vision: diagrams | 1306 | 1266 | Claude Sonnet 4.6 |
| LMArena Vision: homework | 1311 | 1268 | Claude Sonnet 4.6 |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| AIME | 92.3% | Not measured | Only Claude Sonnet 4.6 measured |
| OTIS Mock AIME | 85.8% | 71.1% | Claude Sonnet 4.6 |
| ProofBench | 45.0% | 18.0% | Claude Sonnet 4.6 |
| LMArena Text: math | 1462 | 1429 | Claude Sonnet 4.6 |
| LMArena Text: mathematical work | 1483 | 1448 | Claude Sonnet 4.6 |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index63
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 84.2% | Claude Sonnet 4.6 |
| LegalBench (Vals AI) | 82.1% | 85.4% | MiniMax M3 |
| CaseLaw (Vals AI) | 64.0% | Not measured | Only Claude Sonnet 4.6 measured |
| CorpFin (Vals AI) | 65.3% | 68.1% | MiniMax M3 |
| TaxEval (Vals AI) | 77.1% | 72.7% | Claude Sonnet 4.6 |
| MortgageTax (Vals AI) | 67.7% | 68.4% | MiniMax M3 |
| MedQA (Vals AI) | 92.1% | Not measured | Only Claude Sonnet 4.6 measured |
| MedCode (Vals AI) | Not measured | 46.3% | Only MiniMax M3 measured |
| SimpleQA Verified | 35.5% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text: science | 1474 | 1452 | Claude Sonnet 4.6 |
| LMArena Text: medicine and healthcare | 1451 | 1441 | Claude Sonnet 4.6 |
| LMArena Text: legal and government | 1470 | 1437 | Claude Sonnet 4.6 |
| LMArena Text: business and finance | 1464 | 1434 | 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 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1284 | 1257 | Claude Sonnet 4.6 |
| Design Arena: UI components | 1269 | 1242 | Claude Sonnet 4.6 |
| Design Arena: game dev | 1258 | 1210 | Claude Sonnet 4.6 |
| Design Arena: data viz | 1278 | 1236 | Claude Sonnet 4.6 |
| Design Arena: 3D | 1234 | 1208 | Claude Sonnet 4.6 |
| Design Arena: all code categories | 1275 | 1247 | Claude Sonnet 4.6 |
| Design Arena: SVG | 1196 | 1161 | Claude Sonnet 4.6 |
| Design Arena: ASCII art | 1235 | 1161 | Claude Sonnet 4.6 |
| LiveBench design | 71.8% | 66.2% | Claude Sonnet 4.6 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index258
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Leader |
|---|---|---|---|
| LiveBench data analysis | 76.1% | 76.2% | MiniMax M3 |
| Public Benefits Bench (Vals AI) | 62.5% | 64.1% | MiniMax M3 |
| SAGE (Vals AI) | 46.6% | 50.6% | MiniMax M3 |
| MedScribe (Vals AI) | Not measured | 87.3% | Only MiniMax M3 measured |
| Vals Multimodal Index | 60.6% | 60.0% | Claude Sonnet 4.6 |
| IFBench | 56.6% | 82.9% | MiniMax M3 |
| Long context reasoning (AA-LCR) | 80.0% | 83.0% | MiniMax M3 |
| DTBench | 89.9% | 78.9% | Claude Sonnet 4.6 |
| LMCA | 46.5% | 33.7% | Claude Sonnet 4.6 |
| Surface Evolver Bench | Not measured | 55.0% | Only MiniMax M3 measured |
| ExploitBench | 23.6% | Not measured | Only Claude Sonnet 4.6 measured |
| LMArena Text | 1458 | 1433 | Claude Sonnet 4.6 |
| LMArena Text: instruction following | 1476 | 1433 | Claude Sonnet 4.6 |
| LMArena Text: creative writing | 1435 | 1404 | Claude Sonnet 4.6 |
| LMArena Vision | 1283 | 1251 | Claude Sonnet 4.6 |
| LMArena Text: English | 1472 | 1443 | Claude Sonnet 4.6 |
| LMArena Text: non-English | 1440 | 1420 | Claude Sonnet 4.6 |
| LMArena Text: Chinese | 1491 | 1466 | Claude Sonnet 4.6 |
| LMArena Text: German | 1428 | 1428 | MiniMax M3 |
| LMArena Text: Japanese | 1420 | 1380 | Claude Sonnet 4.6 |
| LMArena Text: Korean | 1410 | 1373 | Claude Sonnet 4.6 |
| LMArena Text: French | 1465 | 1444 | Claude Sonnet 4.6 |
| LMArena Text: Spanish | 1464 | 1433 | Claude Sonnet 4.6 |
| LMArena Text: Russian | 1440 | 1426 | Claude Sonnet 4.6 |
| LMArena Text: Polish | 1443 | 1423 | Claude Sonnet 4.6 |
| LMArena Text: multi-turn | 1464 | 1443 | Claude Sonnet 4.6 |
| LMArena Text: longer queries | 1479 | 1446 | Claude Sonnet 4.6 |
| LMArena Text: writing and language | 1444 | 1419 | Claude Sonnet 4.6 |
| LMArena Text: entertainment and media | 1431 | 1403 | Claude Sonnet 4.6 |
| LMArena Vision: English | 1298 | 1263 | Claude Sonnet 4.6 |
| LMArena Vision: Chinese | 1307 | 1311 | MiniMax M3 |
| LMArena Vision: reading text | 1296 | 1259 | Claude Sonnet 4.6 |
| LMArena Vision: humor | 1248 | 1235 | Claude Sonnet 4.6 |
| LMArena Vision: recognizing things | 1195 | 1197 | MiniMax M3 |
| LMArena Vision: creative writing | 1272 | 1234 | Claude Sonnet 4.6 |
| LMArena Document | 1482 | 1435 | Claude Sonnet 4.6 |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | 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 M3 costs less
Repository review
50K input + 3K output tokens
MiniMax M3 costs less
Agent loop
200K input + 10K output tokens
MiniMax M3 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 M3 |
|---|---|---|
| Maker | Anthropic | MiniMax |
| Weights | No public weights listed | Open weights |
| Released | February 17, 2026 | May 31, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $3.00 | $0.30 |
| Output $/Mtok | $15.00 | $1.20 |
| Coding index | 57.3 | 39.2 |
| Independent measurements behind it | 5 | 6 |
| Cost per solved task | $1.68 | $0.56 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.6 better than MiniMax M3 for coding?
Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 5 benchmarks against 6. Pick MiniMax M3 for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.56 against $1.68).
Which is cheaper, Claude Sonnet 4.6 or MiniMax M3?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and MiniMax M3 $0.56.
Which has the bigger context window, Claude Sonnet 4.6 or MiniMax M3?
MiniMax M3, with 1.05M tokens against 1M.
How many benchmarks is the Claude Sonnet 4.6 vs MiniMax M3 comparison based on?
104 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 M3's on 6. Where only one model has a result, the page says so instead of naming a winner.