Model comparison
Claude Sonnet 4 vs MiniMax-M2.5
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 38.3 on the Noometry Index. MiniMax-M2.5 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 . 25 shared benchmarks.
MiniMaxSummary
- They share 25 benchmarks with published results for both. Claude Sonnet 4 scores higher in 6 categories and MiniMax-M2.5 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 26.9.
- The biggest single-benchmark swing is ARC-AGI-1: 40% for Claude Sonnet 4 and 63.7% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- MiniMax-M2.5 accepts more context: 205K tokens versus 200K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | MiniMax-M2.5 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 40.8 | 38.3 |
| Released | 2025-05-22 | 2026-02-12 |
| 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 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Claude Sonnet 4: 43.5 (#88), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | 75.8% |
| LMArena Coding | 1414 | 1381 |
| ALE-Bench | 655.35 | 618.17 |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), MiniMax-M2.5: 30.4 (#77)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
| Vending-Bench 2 | — | -23.16 |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 5.9% | 4.9% |
| Kagi LLM Benchmark | 73% | 55.2% |
| ARC-AGI-1 | 40% | 63.7% |
| LMArena Hard Prompts | 1372 | 1372 |
| Epoch Capabilities Index | 141.69 | 146.68 |
| SimpleBench | 45.5% | — |
| NYT Connections (extended) | — | 16.8% |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1375 | 1378 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | — | 4% |
| 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: 41.8 (#108), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 10.3% | 9.1% |
| LMArena Expert | 1372 | 1379 |
| 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: 26.2 (#121), MiniMax-M2.5: —
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Too close to call
Claude Sonnet 4: 46.7 (#156), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1333 | 1338 |
| LMArena Chinese | 1350 | 1393 |
| LMArena French | 1363 | 1362 |
| LMArena German | 1331 | 1362 |
| LMArena Japanese | 1302 | 1171 |
| LMArena Korean | 1291 | 1232 |
| LMArena Russian | 1355 | 1358 |
| LMArena Spanish | 1357 | 1354 |
Instruction Following Too close to call
Claude Sonnet 4: 71.7 (#145), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1353 |
| IFEval | 84% | — |
Long Context MiniMax-M2.5 leads
Claude Sonnet 4: 33.7 (#259), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1398 | 1366 |
| Fiction.LiveBench | 46.9% | — |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Claude Sonnet 4 | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1351 | 1359 |
| LMArena Creative Writing | 1345 | 1331 |
| EQ-Bench Creative Writing | 1483 | 1361 |
| LMArena Multi-Turn | 1376 | 1364 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than MiniMax-M2.5?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 38.3 on the Noometry Index. MiniMax-M2.5 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-M2.5?
MiniMax-M2.5 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-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 43.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.5 does, with 205K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and MiniMax-M2.5 share?
25 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and MiniMax-M2.5 has 33.