Model comparison
Inkling vs MiniMax-M3
Inkling and MiniMax-M3 score almost the same on the Noometry Index (44.1 vs 43.8), so choose on price, context window or the category you care about most.
Last verified . 32 shared benchmarks.
MiniMaxSummary
- They share 32 benchmarks with published results for both. Inkling scores higher in 4 categories and MiniMax-M3 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 30.1.
- The biggest single-benchmark swing is ProofBench: 0% for Inkling and 18% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- MiniMax-M3 accepts more context: 1M tokens versus 66K.
Side by side
| Inkling | MiniMax-M3 | |
|---|---|---|
| Provider | Thinking Machines Lab | MiniMax |
| Noometry Index | 44.1 | 43.8 |
| Released | 2026-07-15 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 66K | 1M |
| Max output | 66K | 512K |
| Input $ / M tokens | $1.87 | $0.30 |
| Output $ / M tokens | $4.68 | $1.20 |
| Results tracked | 41 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Inkling: 34.5 (#234), MiniMax-M3: 41.8 (#118)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| FrontierCode | 14% | 14.7% |
| LMArena WebDev | 1413 | 1482 |
| SciCode | 47% | 47.1% |
| LMArena Coding | 1464 | 1469 |
| ALE-Bench | 946 | 640.02 |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
Agentic & Tool Use Inkling leads
Inkling: 29.6 (#85), MiniMax-M3: 22.6 (#130)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 33.8% | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| τ²-bench Banking | 25% | — |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning Inkling leads
Inkling: 40.4 (#56), MiniMax-M3: 30.1 (#87)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| SimpleBench | 50% | 45.8% |
| CritPt | 5.4% | 3.7% |
| Chess Puzzles | 21% | 14% |
| LMArena Hard Prompts | 1451 | 1447 |
| DTBench | 87.5% | 78.9% |
| LMCA | 37.6% | 33.7% |
| Epoch Capabilities Index | 148.54 | 146.95 |
| ARC-AGI-2 | 36.5% | — |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 79.5% | — |
| Mystery Game Puzzles | — | 8% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |
Math MiniMax-M3 leads
Inkling: 31.3 (#225), MiniMax-M3: 40.0 (#95)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 71.1% |
| ProofBench | 0% | 18% |
| LMArena Math | 1479 | 1429 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
Knowledge MiniMax-M3 leads
Inkling: 55.1 (#49), MiniMax-M3: 58.4 (#35)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 88.3% | 90.9% |
| LMArena Expert | 1465 | 1461 |
| SimpleQA Verified | 40.3% | — |
Multimodal Not comparable
Inkling: —, MiniMax-M3: 40.2 (#51)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual Inkling leads
Inkling: 54.0 (#52), MiniMax-M3: 53.0 (#75)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1434 | 1420 |
| LMArena Chinese | 1490 | 1463 |
| LMArena French | 1458 | 1447 |
| LMArena German | 1446 | 1426 |
| LMArena Japanese | 1429 | 1381 |
| LMArena Korean | 1404 | 1372 |
| LMArena Russian | 1429 | 1428 |
| LMArena Spanish | 1448 | 1432 |
Instruction Following Too close to call
Inkling: 75.1 (#71), MiniMax-M3: 75.5 (#62)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1433 |
Long Context Too close to call
Inkling: 43.8 (#86), MiniMax-M3: 44.2 (#72)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1434 | 1445 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), MiniMax-M3: 62.1 (#83)
| Benchmark | Inkling | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1441 | 1433 |
| LMArena Creative Writing | 1387 | 1404 |
| EQ-Bench 4 | 1226 | 1150 |
| LMArena Multi-Turn | 1436 | 1442 |
| EQ-Bench Creative Writing | 1611 | — |
Frequently asked questions
Is Inkling better than MiniMax-M3?
Inkling and MiniMax-M3 score almost the same on the Noometry Index (44.1 vs 43.8), so choose on price, context window or the category you care about most.
Which is cheaper, Inkling or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 66K.
How many benchmarks do Inkling and MiniMax-M3 share?
32 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and MiniMax-M3 has 41.