Model comparison
Gemini 2.0 Flash-Lite vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.5 to 37.3 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
MiniMaxSummary
- They share 20 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 0 categories and MiniMax-M3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 34.6.
- The biggest single-benchmark swing is DTBench: 52.5% for Gemini 2.0 Flash-Lite and 78.9% for MiniMax-M3.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash-Lite | MiniMax-M3 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 37.3 | 43.5 |
| Released | 2025-02-05 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 512K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 32 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 37.4 (#181), MiniMax-M3: 41.5 (#111)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1322 | 1470 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| LiveBench Coding | 47.1% | — |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, MiniMax-M3: 22.5 (#121)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 21.2 (#203), MiniMax-M3: 29.3 (#83)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1447 |
| DTBench | 52.5% | 78.9% |
| ForecastBench | 57.1 | 61.4 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| LiveBench Reasoning | 50.1% | — |
| Mystery Game Puzzles | — | 8% |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 147 |
| LiveBench | 54.3% | — |
Math MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 31.8 (#192), MiniMax-M3: 39.1 (#83)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1309 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
| Omni-MATH | 37.4% | — |
| LiveBench Math | 58.1% | — |
Knowledge MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 34.6 (#185), MiniMax-M3: 58.4 (#32)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1305 | 1462 |
| GPQA Diamond | — | 90.9% |
| MMLU-Pro | 72% | — |
| GPQA (HELM) | 50% | — |
Multimodal MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 30.6 (#103), MiniMax-M3: 39.5 (#45)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1100 | 1254 |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 46.2 (#156), MiniMax-M3: 53.2 (#70)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1323 | 1420 |
| LMArena Chinese | 1339 | 1465 |
| LMArena French | 1346 | 1445 |
| LMArena German | 1306 | 1424 |
| LMArena Japanese | 1302 | 1381 |
| LMArena Korean | 1325 | 1372 |
| LMArena Russian | 1328 | 1430 |
| LMArena Spanish | 1313 | 1431 |
Instruction Following MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 70.6 (#158), MiniMax-M3: 75.7 (#56)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1305 | 1433 |
| LiveBench Instruction Following | 78.3% | — |
| IFEval | 82.4% | — |
Long Context MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 40.1 (#155), MiniMax-M3: 44.2 (#68)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1321 | 1445 |
Writing & Preference MiniMax-M3 leads
Gemini 2.0 Flash-Lite: 51.9 (#172), MiniMax-M3: 62.3 (#79)
| Benchmark | Gemini 2.0 Flash-Lite | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1330 | 1433 |
| LMArena Creative Writing | 1319 | 1405 |
| LMArena Multi-Turn | 1307 | 1441 |
| WildBench | 79% | — |
| EQ-Bench 4 | — | 1150 |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 37.3 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 37.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and MiniMax-M3 share?
20 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and MiniMax-M3 has 41.