Model comparison
Gemini 2.5 Flash-Lite vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 3.1× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 1 category and MiMo-V2-Pro in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2-Pro leads 40.8 to 32.1.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
Side by side
| Gemini 2.5 Flash-Lite | MiMo-V2-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 36.4 | 42.4 |
| Released | 2025-06-17 | 2026-03-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $0.43 |
| Output $ / M tokens | $0.40 | $0.87 |
| Results tracked | 33 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Gemini 2.5 Flash-Lite: 38.0 (#167), MiMo-V2-Pro: 43.4 (#76)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1373 | 1476 |
| ALE-Bench | 325.9 | 785.17 |
| LMArena WebDev | — | 1433 |
| WeirdML | 35.2% | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash-Lite: 27.8 (#89), MiMo-V2-Pro: —
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
Reasoning Too close to call
Gemini 2.5 Flash-Lite: 21.5 (#196), MiMo-V2-Pro: 21.3 (#200)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1457 |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
| Epoch Capabilities Index | 133.93 | — |
Math MiMo-V2-Pro leads
Gemini 2.5 Flash-Lite: 35.5 (#144), MiMo-V2-Pro: 36.7 (#104)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1373 | 1447 |
| Omni-MATH | 48% | — |
Knowledge MiMo-V2-Pro leads
Gemini 2.5 Flash-Lite: 32.1 (#206), MiMo-V2-Pro: 40.8 (#106)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1373 | 1479 |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 28.6 (#109), MiMo-V2-Pro: —
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual MiMo-V2-Pro leads
Gemini 2.5 Flash-Lite: 49.5 (#129), MiMo-V2-Pro: 52.9 (#77)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1369 | 1416 |
| LMArena Chinese | 1404 | 1455 |
| LMArena French | 1388 | 1470 |
| LMArena German | 1390 | 1417 |
| LMArena Japanese | 1359 | 1366 |
| LMArena Korean | 1358 | 1401 |
| LMArena Russian | 1373 | 1427 |
| LMArena Spanish | 1396 | 1458 |
Instruction Following MiMo-V2-Pro leads
Gemini 2.5 Flash-Lite: 70.2 (#163), MiMo-V2-Pro: 76.2 (#46)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1366 | 1444 |
| IFEval | 81% | — |
Long Context MiMo-V2-Pro leads
Gemini 2.5 Flash-Lite: 33.3 (#257), MiMo-V2-Pro: 41.5 (#133)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1373 | 1455 |
| Fiction.LiveBench | 47.2% | — |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Gemini 2.5 Flash-Lite: 57.0 (#130), MiMo-V2-Pro: 62.9 (#67)
| Benchmark | Gemini 2.5 Flash-Lite | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1379 | 1436 |
| LMArena Creative Writing | 1366 | 1415 |
| LMArena Multi-Turn | 1367 | 1456 |
| WildBench | 81.8% | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 3.1× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or MiMo-V2-Pro?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.
Is Gemini 2.5 Flash-Lite or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 38.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 2.5 Flash-Lite and MiMo-V2-Pro share?
18 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and MiMo-V2-Pro has 23.