Model comparison
Claude 3 Sonnet vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
MiniMaxSummary
- They share 15 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and MiniMax-M2 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2 leads 37.3 to 10.7.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | MiniMax-M2 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 29.0 | 37.4 |
| Released | 2024-02-29 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 30 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Claude 3 Sonnet: 29.6 (#302), MiniMax-M2: 39.3 (#159)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1223 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Sonnet: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), MiniMax-M2: 19.4 (#258)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math MiniMax-M2 leads
Claude 3 Sonnet: 10.7 (#310), MiniMax-M2: 37.3 (#160)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1213 | 1352 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
Knowledge MiniMax-M2 leads
Claude 3 Sonnet: 21.1 (#276), MiniMax-M2: 37.0 (#163)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1173 | 1337 |
| GPQA Diamond | 40.6% | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), MiniMax-M2: —
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual MiniMax-M2 leads
Claude 3 Sonnet: 37.8 (#234), MiniMax-M2: 45.3 (#171)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1205 | 1313 |
| LMArena Chinese | 1189 | 1366 |
| LMArena French | 1229 | 1335 |
| LMArena German | 1204 | 1355 |
| LMArena Russian | 1227 | 1331 |
| LMArena Spanish | 1204 | 1326 |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
Instruction Following MiniMax-M2 leads
Claude 3 Sonnet: 62.8 (#235), MiniMax-M2: 70.2 (#166)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1328 |
Long Context MiniMax-M2 leads
Claude 3 Sonnet: 36.7 (#228), MiniMax-M2: 40.5 (#153)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1211 | 1331 |
Writing & Preference MiniMax-M2 leads
Claude 3 Sonnet: 42.1 (#238), MiniMax-M2: 53.0 (#162)
| Benchmark | Claude 3 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1218 | 1340 |
| LMArena Creative Writing | 1186 | 1286 |
| LMArena Multi-Turn | 1227 | 1361 |
Frequently asked questions
Is Claude 3 Sonnet better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and MiniMax-M2 share?
15 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and MiniMax-M2 has 21.