Model comparison
Gemini 3.5 Flash Lite vs MiniMax-M2.7
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 1.6× less per token, which makes it the better buy when Gemini 3.5 Flash Lite's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Google
MiniMaxSummary
- They share 25 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 8 categories and MiniMax-M2.7 in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.1 to 37.7.
- The biggest single-benchmark swing is NYT Connections (extended): 60.4% for Gemini 3.5 Flash Lite and 24.7% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.30 / $2.50 for Gemini 3.5 Flash Lite.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.5 Flash Lite | MiniMax-M2.7 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 41.5 | 37.7 |
| Released | 2026-07-21 | 2026-03-18 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 205K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $2.50 | $1.20 |
| Results tracked | 39 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.5 Flash Lite: 42.4 (#104), MiniMax-M2.7: 41.8 (#120)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1440 | 1398 |
| SciCode | 41.3% | 47% |
| WeirdML | 39% | 37% |
| LMArena Coding | 1453 | 1454 |
| ALE-Bench | 765.27 | 599.25 |
Agentic & Tool Use Too close to call
Gemini 3.5 Flash Lite: 25.7 (#107), MiniMax-M2.7: 25.1 (#111)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| APEX-Agents | 29.3% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
| GDP.pdf | 10% | — |
Reasoning Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 27.8 (#114), MiniMax-M2.7: 19.7 (#253)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| NYT Connections (extended) | 60.4% | 24.7% |
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1441 | 1422 |
| Epoch Capabilities Index | 145.13 | 145.85 |
| ARC-AGI-2 | 10.3% | — |
| ARC-AGI-1 | 53.5% | — |
| Chess Puzzles | 22% | — |
| Thematic Generalization | — | 39.3% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
Math Too close to call
Gemini 3.5 Flash Lite: 25.9 (#264), MiniMax-M2.7: 25.9 (#263)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| ProofBench | 13% | 3% |
| LMArena Math | 1433 | 1420 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
Knowledge Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 50.1 (#72), MiniMax-M2.7: 37.7 (#152)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1435 | 1444 |
| GPQA Diamond | 83.3% | — |
| Vectara Hallucination Rate | — | 12.9% |
Multimodal Not comparable
Gemini 3.5 Flash Lite: 41.1 (#40), MiniMax-M2.7: —
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1268 | — |
Multilingual Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 53.5 (#63), MiniMax-M2.7: 50.3 (#123)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1427 | 1382 |
| LMArena Chinese | 1469 | 1441 |
| LMArena French | 1451 | 1421 |
| LMArena German | 1454 | 1398 |
| LMArena Japanese | 1427 | 1262 |
| LMArena Korean | 1407 | 1313 |
| LMArena Russian | 1443 | 1383 |
| LMArena Spanish | 1442 | 1403 |
Instruction Following Too close to call
Gemini 3.5 Flash Lite: 74.8 (#85), MiniMax-M2.7: 74.1 (#103)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1405 |
Long Context Too close to call
Gemini 3.5 Flash Lite: 43.9 (#84), MiniMax-M2.7: 43.3 (#99)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1435 | 1419 |
Writing & Preference Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 64.2 (#57), MiniMax-M2.7: 58.9 (#112)
| Benchmark | Gemini 3.5 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1435 | 1405 |
| LMArena Creative Writing | 1420 | 1354 |
| LMArena Multi-Turn | 1445 | 1412 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than MiniMax-M2.7?
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 1.6× less per token, which makes it the better buy when Gemini 3.5 Flash Lite's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash Lite or MiniMax-M2.7?
MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Gemini 3.5 Flash Lite lists at $0.30 and $2.50.
Is Gemini 3.5 Flash Lite or MiniMax-M2.7 better for coding?
They score almost the same on coding (42.4 vs 41.8); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 3.5 Flash Lite does, with 1.05M tokens against 205K.
How many benchmarks do Gemini 3.5 Flash Lite and MiniMax-M2.7 share?
25 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and MiniMax-M2.7 has 30.