Model comparison
MiniMax-M3 vs Yi-Lightning
MiniMax-M3 is the stronger model overall, scoring 43.8 to 37.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Yi-Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 35.4.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M3 | Yi-Lightning | |
|---|---|---|
| Provider | MiniMax | 01.AI |
| Noometry Index | 43.8 | 37.1 |
| Released | 2026-06-01 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Yi-Lightning: 27.4 (#320)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1469 | 1312 |
| FrontierCode | 14.7% | — |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Yi-Lightning: —
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), Yi-Lightning: 25.9 (#139)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1302 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Yi-Lightning: 36.2 (#172)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Math | 1429 | 1300 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Yi-Lightning: 35.4 (#185)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1461 | 1286 |
| GPQA Diamond | 90.9% | — |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Yi-Lightning: —
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Yi-Lightning: 42.2 (#196)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1420 | 1269 |
| LMArena Chinese | 1463 | 1320 |
| LMArena French | 1447 | 1305 |
| LMArena German | 1426 | 1267 |
| LMArena Japanese | 1381 | 1228 |
| LMArena Korean | 1372 | 1192 |
| LMArena Russian | 1428 | 1255 |
| LMArena Spanish | 1432 | 1315 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Yi-Lightning: 67.4 (#196)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1433 | 1278 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Yi-Lightning: 39.4 (#181)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1445 | 1297 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Yi-Lightning: 50.2 (#184)
| Benchmark | MiniMax-M3 | Yi-Lightning |
|---|---|---|
| LMArena Text | 1433 | 1302 |
| LMArena Creative Writing | 1404 | 1280 |
| LMArena Multi-Turn | 1442 | 1311 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Yi-Lightning?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 37.1 on the Noometry Index.
Is MiniMax-M3 or Yi-Lightning better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 27.4 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and Yi-Lightning share?
17 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Yi-Lightning has 18.