Model comparison
Claude Sonnet 5 vs MiniMax-M3
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 43.8 on the Noometry Index. MiniMax-M3 costs 7.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 40 shared benchmarks.
MiniMaxSummary
- They share 40 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and MiniMax-M3 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 40.0.
- The biggest single-benchmark swing is GBAEval: 65.3% for Claude Sonnet 5 and 0.9% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | MiniMax-M3 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 54.6 | 43.8 |
| Released | 2026-06-29 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 512K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $10 | $1.20 |
| Results tracked | 51 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), MiniMax-M3: 41.8 (#118)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| FrontierCode | 42.7% | 14.7% |
| LMArena WebDev | 1541 | 1482 |
| SciCode | 54.3% | 47.1% |
| LMArena Coding | 1483 | 1469 |
| ALE-Bench | 1,463 | 640.02 |
| DeepSWE | 53.8% | — |
| CursorBench | 34.1% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), MiniMax-M3: 22.6 (#130)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 54.5% | 37.7% |
| GBAEval | 65.3% | 0.9% |
| Vending-Bench 2 | 6,378 | 2,158 |
| OSWorld 2.0 | — | 4.6% |
| LMArena Search | 1194 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), MiniMax-M3: 30.1 (#87)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| SimpleBench | 60.6% | 45.8% |
| NYT Connections (extended) | 75.1% | 65.1% |
| CritPt | 16.9% | 3.7% |
| Chess Puzzles | 35% | 14% |
| LMArena Hard Prompts | 1461 | 1447 |
| Mystery Game Puzzles | 35% | 8% |
| DTBench | 92.5% | 78.9% |
| LMCA | 50% | 33.7% |
| Surface Evolver Bench | 60% | 55% |
| Epoch Capabilities Index | 156.21 | 146.95 |
| ForecastBench | 61.1 | 61.4 |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), MiniMax-M3: 40.0 (#95)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 71.1% |
| ProofBench | 77% | 18% |
| LMArena Math | 1467 | 1429 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
Knowledge MiniMax-M3 leads
Claude Sonnet 5: 55.6 (#47), MiniMax-M3: 58.4 (#35)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 90.5% | 90.9% |
| LMArena Expert | 1490 | 1461 |
| SimpleQA Verified | 33.7% | — |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#31), MiniMax-M3: 40.2 (#51)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1274 | 1253 |
| LMArena Document | 1466 | 1435 |
| Blueprint-Bench 2 | 24.9% | — |
Multilingual Too close to call
Claude Sonnet 5: 53.8 (#55), MiniMax-M3: 53.0 (#75)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1431 | 1420 |
| LMArena Chinese | 1477 | 1463 |
| LMArena French | 1460 | 1447 |
| LMArena German | 1440 | 1426 |
| LMArena Japanese | 1422 | 1381 |
| LMArena Korean | 1411 | 1372 |
| LMArena Russian | 1451 | 1428 |
| LMArena Spanish | 1437 | 1432 |
Instruction Following Too close to call
Claude Sonnet 5: 76.3 (#41), MiniMax-M3: 75.5 (#62)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1433 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#55), MiniMax-M3: 44.2 (#72)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1463 | 1445 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), MiniMax-M3: 62.1 (#83)
| Benchmark | Claude Sonnet 5 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1442 | 1433 |
| LMArena Creative Writing | 1416 | 1404 |
| EQ-Bench 4 | 1236 | 1150 |
| LMArena Multi-Turn | 1454 | 1442 |
| EQ-Bench Creative Writing | 1794 | — |
Frequently asked questions
Is Claude Sonnet 5 better than MiniMax-M3?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 43.8 on the Noometry Index. MiniMax-M3 costs 7.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or MiniMax-M3 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 5 and MiniMax-M3 share?
40 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and MiniMax-M3 has 41.