Model comparison
Claude Sonnet 4 vs MiniMax-M2.1
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 11× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. Claude Sonnet 4 scores higher in 5 categories and MiniMax-M2.1 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 4 leads 38.3 to 27.7.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- MiniMax-M2.1 accepts more context: 205K tokens versus 200K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | MiniMax-M2.1 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 40.6 | 38.4 |
| Released | 2025-05-22 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | 200K | 205K |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $0.30 |
| Output $ / M tokens | $15 | $1.20 |
| Results tracked | 58 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 44.0 (#70), MiniMax-M2.1: 40.1 (#132)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1414 | 1421 |
| ALE-Bench | 655.35 | 623.83 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1384 |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.3 (#29), MiniMax-M2.1: 27.7 (#91)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 23.0 (#169), MiniMax-M2.1: 15.8 (#301)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1410 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| NYT Connections (extended) | — | 11.2% |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 41.5 (#71), MiniMax-M2.1: 35.6 (#142)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1375 | 1396 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.6 (#99), MiniMax-M2.1: 37.7 (#143)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 10.3% | 11.8% |
| LMArena Expert | 1371 | 1432 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 25.6 (#116), MiniMax-M2.1: —
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual MiniMax-M2.1 leads
Claude Sonnet 4: 46.9 (#151), MiniMax-M2.1: 50.2 (#123)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1333 | 1378 |
| LMArena Chinese | 1351 | 1430 |
| LMArena French | 1364 | 1405 |
| LMArena German | 1331 | 1380 |
| LMArena Japanese | 1301 | 1287 |
| LMArena Korean | 1293 | 1297 |
| LMArena Russian | 1355 | 1386 |
| LMArena Spanish | 1356 | 1396 |
Instruction Following MiniMax-M2.1 leads
Claude Sonnet 4: 71.8 (#141), MiniMax-M2.1: 74.0 (#108)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1375 | 1399 |
| IFEval | 84% | — |
Long Context MiniMax-M2.1 leads
Claude Sonnet 4: 33.6 (#254), MiniMax-M2.1: 43.2 (#98)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1398 | 1416 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference MiniMax-M2.1 leads
Claude Sonnet 4: 57.3 (#127), MiniMax-M2.1: 58.5 (#114)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1351 | 1392 |
| LMArena Creative Writing | 1345 | 1362 |
| LMArena Multi-Turn | 1376 | 1396 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than MiniMax-M2.1?
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 11× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or MiniMax-M2.1?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or MiniMax-M2.1 better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and MiniMax-M2.1 share?
19 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and MiniMax-M2.1 has 22.