Model comparison
Claude 3.5 Sonnet vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 34.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
MiniMaxSummary
- They share 15 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 2 categories and MiniMax-M2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2 leads 37.3 to 19.2.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | MiniMax-M2 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 34.6 | 37.4 |
| Released | 2024-06-20 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 60 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.5 Sonnet: 39.0 (#165), MiniMax-M2: 39.3 (#159)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1342 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1297 |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), MiniMax-M2: 25.1 (#109)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 160.6 |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), MiniMax-M2: 19.4 (#258)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1357 |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math MiniMax-M2 leads
Claude 3.5 Sonnet: 19.2 (#288), MiniMax-M2: 37.3 (#160)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1307 | 1352 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge MiniMax-M2 leads
Claude 3.5 Sonnet: 28.6 (#245), MiniMax-M2: 37.0 (#163)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1265 | 1337 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), MiniMax-M2: —
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual MiniMax-M2 leads
Claude 3.5 Sonnet: 43.2 (#185), MiniMax-M2: 45.3 (#171)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1283 | 1313 |
| LMArena Chinese | 1272 | 1366 |
| LMArena French | 1305 | 1335 |
| LMArena German | 1297 | 1355 |
| LMArena Russian | 1306 | 1331 |
| LMArena Spanish | 1290 | 1326 |
| LMArena Japanese | 1234 | — |
| LMArena Korean | 1200 | — |
Instruction Following MiniMax-M2 leads
Claude 3.5 Sonnet: 68.8 (#182), MiniMax-M2: 70.2 (#166)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1328 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#167), MiniMax-M2: 40.5 (#153)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1311 | 1331 |
Writing & Preference Too close to call
Claude 3.5 Sonnet: 52.9 (#164), MiniMax-M2: 53.0 (#162)
| Benchmark | Claude 3.5 Sonnet | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1298 | 1340 |
| LMArena Creative Writing | 1292 | 1286 |
| LMArena Multi-Turn | 1326 | 1361 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or MiniMax-M2 better for coding?
They score almost the same on coding (39.0 vs 39.3); test both on your own repository before choosing.
How many benchmarks do Claude 3.5 Sonnet and MiniMax-M2 share?
15 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and MiniMax-M2 has 21.