Claude Opus 5.5 vs MiniMax M3
Updated October 21, 2026. 83 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Claude Opus 5.5 for coding: it scores 92.2 on the Vibe Coding Index against 57.8 for MiniMax M3.
Pick MiniMax M3 when output tokens cost 16.7x less, or when the context window is larger, 1.05M against 1M tokens.
- Shared results
- 83
- Claude Opus 5.5 only
- 24
- MiniMax M3 only
- 33
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
Claude Opus 5.5
Claude Opus 5.5 scores 92.2 against 57.8.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Claude Opus 5.5
Claude Opus 5.5 leads, 57.6 against 29.2.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only MiniMax M3 has a AA Agentic Index result, 29.5.
Directional only
Reasoning
GPQA Diamond
No call
Only MiniMax M3 has a GPQA Diamond result, 92.7%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M3 has a MMLU Pro result, 84.2%.
Directional only
Web design
Design Arena: websites
Claude Opus 5.5
Claude Opus 5.5 leads, 1335 against 1257.
Same board, both measured
General
Vals Index
No call
Only Claude Opus 5.5 has a Vals Index result, 70.2%.
Directional only
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 Opus 5.5 $0.014, MiniMax M3 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M3 has the number, $0.56.
Directional only
At a glance
- Coding index
- Claude Opus 5.5 92.2 from 2 benchmarks, MiniMax M3 57.8 from 2 benchmarks.
- Widest category
- Math, 34.2 points apart on average over 4 shared benchmarks.
- Widest single gap
- ProofBench: Claude Opus 5.5 100.0% against MiniMax M3 18.0%, 82.0 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 5.5 $20.00 against MiniMax M3 $1.20 per million output tokens, 16.7x apart.
- Context window
- Claude Opus 5.5 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 Opus 5.5 | Bars | MiniMax M3 | Ties |
|---|---|---|---|---|
| Coding | 17 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 12 | 0 | ||
| Reasoning | 9 | 1 | ||
| Math | 4 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 8 | 0 | ||
| General | 24 | 1 | ||
| All shared boards | 81 | 2 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index170
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| LiveBench coding | 96.3% | 70.9% | Claude Opus 5.5 |
| LMArena WebDev | 1807 | 1482 | Claude Opus 5.5 |
| AA Coding Index | Not measured | 58.6 | Only MiniMax M3 measured |
| LiveCodeBench (Vals AI) | Not measured | 82.2% | Only MiniMax M3 measured |
| SWE-bench Verified (Vals AI) | Not measured | 75.0% | Only MiniMax M3 measured |
| Terminal-Bench 4 (Vals AI) | 65.2% | 1.0% | Claude Opus 5.5 |
| Vibe Code Bench (Vals AI) | 90.3% | 47.6% | Claude Opus 5.5 |
| Code migration (Vals AI) | 66.7% | 19.9% | Claude Opus 5.5 |
| ProgramBench (Vals AI) | 18.5% | Not measured | Only Claude Opus 5.5 measured |
| IOI (Vals AI) | 95.1% | Not measured | Only Claude Opus 5.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 87.6% | 53.6% | Claude Opus 5.5 |
| SWE-bench Multimodal (Vals AI) | 70.2% | 33.3% | Claude Opus 5.5 |
| Vibe Code Bench 1-100 (Vals AI) | 30.4% | 9.2% | Claude Opus 5.5 |
| SkillsBench (Vals AI) | Not measured | 51.5% | Only MiniMax M3 measured |
| CyberBench (Vals AI) | 74.6% | 65.0% | Claude Opus 5.5 |
| SciCode | 66.9% | 47.1% | Claude Opus 5.5 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 42.4% | Only MiniMax M3 measured |
| FrontierCode | 54.6% | 14.7% | Claude Opus 5.5 |
| FrontierSWE | 62.3% | Not measured | Only Claude Opus 5.5 measured |
| MirrorCode | 77.4% | Not measured | Only Claude Opus 5.5 measured |
| ALE-Bench | 2147.4 | 640.0 | Claude Opus 5.5 |
| LMArena Text: coding | 1545 | 1470 | Claude Opus 5.5 |
| LMArena Text: software and IT | 1538 | 1466 | Claude Opus 5.5 |
| LMArena WebDev: React | 1855 | 1478 | Claude Opus 5.5 |
| LMArena WebDev: HTML | 1753 | 1455 | Claude Opus 5.5 |
| LMArena WebDev: from an image | 1753 | 1470 | Claude Opus 5.5 |
| Neither model has a result on the other 12 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 57.6 | 29.2 | Claude Opus 5.5 |
| Epoch Capabilities Index | 168.8 | 146.9 | Claude Opus 5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index120
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 29.5 | Only MiniMax M3 measured |
| Design Arena: agents building web apps | 1316 | 1200 | Claude Opus 5.5 |
| Design Arena: agents building full-stack apps | Not measured | 1197 | Only MiniMax M3 measured |
| Design Arena: agents building mobile apps | 1311 | 1169 | Claude Opus 5.5 |
| Design Arena: agents building Android apps | Not measured | 1164 | Only MiniMax M3 measured |
| Design Arena: agents building games | Not measured | 1158 | Only MiniMax M3 measured |
| Design Arena: HTML slides | Not measured | 1180 | Only MiniMax M3 measured |
| Design Arena: PowerPoint slides | Not measured | 1205 | Only MiniMax M3 measured |
| Design Arena: spreadsheets | 1359 | 1021 | Claude Opus 5.5 |
| LiveBench research | 85.0% | 68.0% | Claude Opus 5.5 |
| LiveBench browser | 80.0% | 8.0% | Claude Opus 5.5 |
| LiveBench long agentic | 85.0% | 12.4% | Claude Opus 5.5 |
| SREBench (Vals AI) | 33.6% | Not measured | Only Claude Opus 5.5 measured |
| Finance Agent (Vals AI) | 58.6% | 48.3% | Claude Opus 5.5 |
| Tax Agent Bench (Vals AI) | 45.6% | 20.6% | Claude Opus 5.5 |
| Legal Research Bench (Vals AI) | 50.5% | 29.8% | Claude Opus 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | 9.2% | Not measured | Only Claude Opus 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 75.9% | 47.8% | Claude Opus 5.5 |
| BioMysteryBench (Vals AI) | 79.3% | Not measured | Only Claude Opus 5.5 measured |
| Terminal-Bench-Science (Vals AI) | 47.1% | Not measured | Only Claude Opus 5.5 measured |
| Vals Science Index | 58.7% | Not measured | Only Claude Opus 5.5 measured |
| Time Horizon Index (Vals AI) | 91.3% | Not measured | Only Claude Opus 5.5 measured |
| CUA-bench (Vals AI) | 14.0% | Not measured | Only Claude Opus 5.5 measured |
| Robo-bench (Vals AI) | 14.6% | Not measured | Only Claude Opus 5.5 measured |
| τ²-Bench Telecom | Not measured | 88.9% | Only MiniMax M3 measured |
| APEX-Agents | 73.5% | 37.7% | Claude Opus 5.5 |
| Remote Labor Index | 21.3% | Not measured | Only Claude Opus 5.5 measured |
| OSWorld 2.0 | Not measured | 4.6% | Only MiniMax M3 measured |
| SpireClimb | 3.3% | Not measured | Only Claude Opus 5.5 measured |
| Vending-Bench 2 | $9,235 | $2,158 | Claude Opus 5.5 |
| LMArena Search | 1213 | Not measured | Only Claude Opus 5.5 measured |
| Neither model has a result on the other 8 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 92.7% | Only MiniMax M3 measured |
| LiveBench reasoning | 92.2% | 74.5% | Claude Opus 5.5 |
| MysteryMechanism (Vals AI) | 49.5% | Not measured | Only Claude Opus 5.5 measured |
| MMMU Pro (Vals AI) | Not measured | 81.2% | Only MiniMax M3 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 92.9% | Only MiniMax M3 measured |
| Humanity's Last Exam (Artificial Analysis run) | 61.4% | 39.0% | Claude Opus 5.5 |
| GPQA Diamond (Epoch AI run) | 90.6% | 90.9% | MiniMax M3 |
| ARC-AGI | 98.5% | Not measured | Only Claude Opus 5.5 measured |
| ARC-AGI-2 | 93.3% | Not measured | Only Claude Opus 5.5 measured |
| SimpleBench | Not measured | 45.8% | Only MiniMax M3 measured |
| Chess puzzles | 67.0% | 13.0% | Claude Opus 5.5 |
| Mystery game puzzles | 71.0% | 8.0% | Claude Opus 5.5 |
| EBR-bench | 71.4% | Not measured | Only Claude Opus 5.5 measured |
| LMArena Text: hard prompts | 1536 | 1447 | Claude Opus 5.5 |
| LMArena Text: expert | 1549 | 1461 | Claude Opus 5.5 |
| LMArena Text: hard prompts in English | 1535 | 1455 | Claude Opus 5.5 |
| LMArena Vision: diagrams | 1345 | 1266 | Claude Opus 5.5 |
| LMArena Vision: homework | 1362 | 1268 | Claude Opus 5.5 |
| Neither model has a result on the other 3 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 71.1% | Claude Opus 5.5 |
| FrontierMath, tiers 1 to 3 | 91.2% | Not measured | Only Claude Opus 5.5 measured |
| FrontierMath, tier 4 | 95.0% | Not measured | Only Claude Opus 5.5 measured |
| ProofBench | 100.0% | 18.0% | Claude Opus 5.5 |
| LMArena Text: math | 1518 | 1429 | Claude Opus 5.5 |
| LMArena Text: mathematical work | 1516 | 1448 | Claude Opus 5.5 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 84.2% | Only MiniMax M3 measured |
| LegalBench (Vals AI) | Not measured | 85.4% | Only MiniMax M3 measured |
| CorpFin (Vals AI) | Not measured | 68.1% | Only MiniMax M3 measured |
| TaxEval (Vals AI) | Not measured | 72.7% | Only MiniMax M3 measured |
| MortgageTax (Vals AI) | Not measured | 68.4% | Only MiniMax M3 measured |
| MedCode (Vals AI) | 49.8% | 46.3% | Claude Opus 5.5 |
| SimpleQA Verified | 72.2% | Not measured | Only Claude Opus 5.5 measured |
| LMArena Text: science | 1524 | 1452 | Claude Opus 5.5 |
| LMArena Text: medicine and healthcare | 1509 | 1441 | Claude Opus 5.5 |
| LMArena Text: legal and government | 1518 | 1437 | Claude Opus 5.5 |
| LMArena Text: business and finance | 1494 | 1434 | Claude Opus 5.5 |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1335 | 1257 | Claude Opus 5.5 |
| Design Arena: UI components | 1390 | 1246 | Claude Opus 5.5 |
| Design Arena: game dev | 1457 | 1210 | Claude Opus 5.5 |
| Design Arena: data viz | 1397 | 1235 | Claude Opus 5.5 |
| Design Arena: 3D | 1477 | 1209 | Claude Opus 5.5 |
| Design Arena: all code categories | 1390 | 1247 | Claude Opus 5.5 |
| Design Arena: SVG | 1332 | 1161 | Claude Opus 5.5 |
| Design Arena: ASCII art | Not measured | 1161 | Only MiniMax M3 measured |
| LiveBench design | 86.9% | 66.2% | Claude Opus 5.5 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index241
| Benchmark | Claude Opus 5.5 | MiniMax M3 | Leader |
|---|---|---|---|
| Vals Index | 70.2% | Not measured | Only Claude Opus 5.5 measured |
| LiveBench data analysis | 80.3% | 76.2% | Claude Opus 5.5 |
| Public Benefits Bench (Vals AI) | 70.6% | 64.1% | Claude Opus 5.5 |
| SAGE (Vals AI) | 45.8% | 50.6% | MiniMax M3 |
| MedScribe (Vals AI) | 91.4% | 87.3% | Claude Opus 5.5 |
| Vals Multimodal Index | Not measured | 60.0% | Only MiniMax M3 measured |
| IFBench | Not measured | 82.9% | Only MiniMax M3 measured |
| Long context reasoning (AA-LCR) | 84.7% | 83.0% | Claude Opus 5.5 |
| DTBench | 98.9% | 78.9% | Claude Opus 5.5 |
| LMCA | 68.2% | 33.7% | Claude Opus 5.5 |
| Surface Evolver Bench | Not measured | 55.0% | Only MiniMax M3 measured |
| Furniture assembly | 83.3% | Not measured | Only Claude Opus 5.5 measured |
| LMArena Text | 1516 | 1433 | Claude Opus 5.5 |
| LMArena Text: instruction following | 1537 | 1433 | Claude Opus 5.5 |
| LMArena Text: creative writing | 1535 | 1404 | Claude Opus 5.5 |
| LMArena Vision | 1321 | 1251 | Claude Opus 5.5 |
| LMArena Text: English | 1519 | 1443 | Claude Opus 5.5 |
| LMArena Text: non-English | 1507 | 1420 | Claude Opus 5.5 |
| LMArena Text: Chinese | 1582 | 1466 | Claude Opus 5.5 |
| LMArena Text: German | Not measured | 1428 | Only MiniMax M3 measured |
| LMArena Text: Japanese | 1534 | 1380 | Claude Opus 5.5 |
| LMArena Text: Korean | Not measured | 1373 | Only MiniMax M3 measured |
| LMArena Text: French | 1493 | 1444 | Claude Opus 5.5 |
| LMArena Text: Spanish | 1508 | 1433 | Claude Opus 5.5 |
| LMArena Text: Russian | 1517 | 1426 | Claude Opus 5.5 |
| LMArena Text: Polish | Not measured | 1423 | Only MiniMax M3 measured |
| LMArena Text: multi-turn | 1501 | 1443 | Claude Opus 5.5 |
| LMArena Text: longer queries | 1532 | 1446 | Claude Opus 5.5 |
| LMArena Text: writing and language | 1532 | 1419 | Claude Opus 5.5 |
| LMArena Text: entertainment and media | 1515 | 1403 | Claude Opus 5.5 |
| LMArena Vision: English | 1317 | 1263 | Claude Opus 5.5 |
| LMArena Vision: Chinese | Not measured | 1311 | Only MiniMax M3 measured |
| LMArena Vision: reading text | 1326 | 1259 | Claude Opus 5.5 |
| LMArena Vision: humor | Not measured | 1235 | Only MiniMax M3 measured |
| LMArena Vision: recognizing things | Not measured | 1197 | Only MiniMax M3 measured |
| LMArena Vision: creative writing | 1320 | 1234 | Claude Opus 5.5 |
| LMArena Document | Not measured | 1435 | Only MiniMax M3 measured |
| Neither model has a result on the other 9 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 5.5 | 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 Opus 5.5 | MiniMax M3 |
|---|---|---|
| Maker | Anthropic | MiniMax |
| Weights | No public weights listed | Open weights |
| Released | September 22, 2026 | May 31, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $4.00 | $0.30 |
| Output $/Mtok | $20.00 | $1.20 |
| Coding index | 92.2 | 57.8 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | $0.56 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 5.5 better than MiniMax M3 for coding?
Pick Claude Opus 5.5 for coding: it scores 92.2 on the Vibe Coding Index against 57.8 for MiniMax M3. Pick MiniMax M3 when output tokens cost 16.7x less, or when the context window is larger, 1.05M against 1M tokens.
Which is cheaper, Claude Opus 5.5 or MiniMax M3?
Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M3 only.
Which has the bigger context window, Claude Opus 5.5 or MiniMax M3?
MiniMax M3, with 1.05M tokens against 1M.
How many benchmarks is the Claude Opus 5.5 vs MiniMax M3 comparison based on?
83 benchmarks have a result for both models as of October 21, 2026. Claude Opus 5.5's coding index rests on 2 independent benchmarks and MiniMax M3's on 2. Where only one model has a result, the page says so instead of naming a winner.