MiMo-V2.5-Pro
| Released | 2026-04-22 |
|---|---|
| Price per 1M | $0.44 in · $0.87 out |
| Overall score | 53.2 · rank 91 |
| Context window | 1,048,576 tokens |
| Provider | Xiaomi |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 53.2 | 91 | 21 |
| Overall: Coding | 53.0 | 85 | 12 |
| Overall: Reasoning | 52.5 | 94 | 6 |
| Overall: Agentic work | 53.5 | 88 | 10 |
| Overall: Frontend | 50.6 | 85 | 6 |
| Coding | 54.0 | 87 | 4 |
| Agents | 53.8 | 82 | 3 |
| Reasoning | 51.6 | 105 | 3 |
| Math | 55.2 | 69 | 1 |
| Knowledge | 49.4 | 97 | 2 |
| Frontend | 49.0 | 78 | 2 |
| General | 56.4 | 52 | 6 |
| Value vs price | +7.3 | 49 |
Evidence
Coding 54.0 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-rebench | 46.5% | SWE-rebench | 2026-07-01 |
| SWE-bench Verified (Vals run) | 74.0% | Vals AI | 2026-09-01 |
| SciCode | 50.2% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 81.4% | Vals AI | 2026-09-01 |
Agents 53.8 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 0.5% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 57.3% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 11.5% | Vals AI | 2026-11-09 |
Reasoning 51.6 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 34.4% | Lech Mazur | 2026-11-10 |
| GPQA Diamond (Vals run) | 82.6% | Vals AI | 2026-09-01 |
| CritPt | 4.0% | Epoch AI | 2026-11-11 |
Math 55.2 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ProofBench v1.1 | 22.0% | Vals AI | 2026-11-09 |
| ProofBench | 22.0% | Epoch AI | 2026-11-11 |
Knowledge 49.4 ±3.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 84.6% | Vals AI | 2026-09-01 |
| Legal Research Bench | 15.9% | Vals AI | 2026-11-09 |
Frontend 49.0 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 34.1% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,479 | LMArena | 2026-11-09 |
General 56.4 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,477 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,198 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,493 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,467 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 39.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 73.7% | EQ-Bench | 2026-11-11 |
Names matched to this model
mimo-v2-5-pro, xiaomi-mimo-v2-5-pro