Model comparison
Gemini 3.1 Pro Preview vs MiMo-V2.5
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 43.0 on the Noometry Index. MiMo-V2.5 costs 26× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 7 categories and MiMo-V2.5 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 27.8.
- The biggest single-benchmark swing is SciCode: 58.9% for Gemini 3.1 Pro Preview and 43.1% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Pro Preview | MiMo-V2.5 | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 56.7 | 43.0 |
| Released | 2026-02-19 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $2 | $0.14 |
| Output $ / M tokens | $12 | $0.28 |
| Results tracked | 71 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.1 Pro Preview: 42.7 (#88), MiMo-V2.5: 43.6 (#75)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1446 | 1438 |
| SciCode | 58.9% | 43.1% |
| LMArena Coding | 1483 | 1469 |
| ALE-Bench | 1,161 | 513.95 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Pro Preview: 37.7 (#33), MiMo-V2.5: —
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#9), MiMo-V2.5: 27.8 (#98)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| CritPt | 17.7% | 3.7% |
| LMArena Hard Prompts | 1484 | 1450 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.92 | — |
| ForecastBench | 59 | — |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 61.8 (#28), MiMo-V2.5: 35.4 (#145)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| ProofBench | 26% | 16% |
| LMArena Math | 1485 | 1436 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.8 (#3), MiMo-V2.5: 40.2 (#109)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1484 | 1459 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |
Multimodal Too close to call
Gemini 3.1 Pro Preview: 38.1 (#60), MiMo-V2.5: 39.0 (#53)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1296 | 1245 |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 57.1 (#11), MiMo-V2.5: 52.0 (#96)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1475 | 1404 |
| LMArena Chinese | 1528 | 1467 |
| LMArena French | 1488 | 1447 |
| LMArena German | 1491 | 1421 |
| LMArena Japanese | 1494 | 1304 |
| LMArena Korean | 1458 | 1363 |
| LMArena Russian | 1496 | 1395 |
| LMArena Spanish | 1480 | 1412 |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.1 (#31), MiMo-V2.5: 75.7 (#55)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1433 |
Long Context Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 47.3 (#17), MiMo-V2.5: 44.1 (#69)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1482 | 1444 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.3 (#36), MiMo-V2.5: 61.8 (#82)
| Benchmark | Gemini 3.1 Pro Preview | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1480 | 1427 |
| LMArena Creative Writing | 1482 | 1392 |
| LMArena Multi-Turn | 1486 | 1445 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than MiMo-V2.5?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 43.0 on the Noometry Index. MiMo-V2.5 costs 26× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Pro Preview or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is Gemini 3.1 Pro Preview or MiMo-V2.5 better for coding?
They score almost the same on coding (42.7 vs 43.6); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.1 Pro Preview and MiMo-V2.5 share?
23 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and MiMo-V2.5 has 23.