Model comparison
MiniMax-M2.5 vs Yi-Lightning
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. MiniMax-M2.5 scores higher in 5 categories and Yi-Lightning in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 27.4.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | Yi-Lightning | |
|---|---|---|
| Provider | MiniMax | 01.AI |
| Noometry Index | 38.3 | 37.1 |
| Released | 2026-02-12 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 48.1 (#58), Yi-Lightning: 27.4 (#320)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1381 | 1312 |
| SWE-bench Verified (bash only) | 75.8% | — |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Yi-Lightning: —
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Yi-Lightning leads
MiniMax-M2.5: 17.5 (#292), Yi-Lightning: 25.9 (#139)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1302 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Epoch Capabilities Index | 146.68 | — |
Math Yi-Lightning leads
MiniMax-M2.5: 26.9 (#253), Yi-Lightning: 36.2 (#172)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Math | 1378 | 1300 |
| ProofBench | 4% | — |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), Yi-Lightning: 35.4 (#185)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1379 | 1286 |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.1 (#152), Yi-Lightning: 42.2 (#196)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1338 | 1269 |
| LMArena Chinese | 1393 | 1320 |
| LMArena French | 1362 | 1305 |
| LMArena German | 1362 | 1267 |
| LMArena Japanese | 1171 | 1228 |
| LMArena Korean | 1232 | 1192 |
| LMArena Russian | 1358 | 1255 |
| LMArena Spanish | 1354 | 1315 |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.5 (#148), Yi-Lightning: 67.4 (#196)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1353 | 1278 |
Long Context Yi-Lightning leads
MiniMax-M2.5: 37.5 (#216), Yi-Lightning: 39.4 (#181)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1366 | 1297 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 53.9 (#153), Yi-Lightning: 50.2 (#184)
| Benchmark | MiniMax-M2.5 | Yi-Lightning |
|---|---|---|
| LMArena Text | 1359 | 1302 |
| LMArena Creative Writing | 1331 | 1280 |
| LMArena Multi-Turn | 1364 | 1311 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Yi-Lightning?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.1 on the Noometry Index.
Is MiniMax-M2.5 or Yi-Lightning better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 27.4 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Yi-Lightning share?
17 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Yi-Lightning has 18.