BlogLLM Benchmark Scores as Published, Side by Side
MiMo-V2.5-Pro: Benchmark Scores as Published
Every result the catalog holds for MiMo-V2.5-Pro: 19 tests in 5 areas, from 3 pages. All were printed by Xiaomi itself. Each number is as printed; nothing is ranked or rescored.
Developer XiaomiReleased 2026-04-27Context window 1MInput TextOutput TextWeights Open (MIT)Data version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AutomationBench | 16% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| JobBench | 25 | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| GDPval-AA v2.1 | 1107 | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Terminal-Bench 2.1 | 65.2% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| DeepSWE v1.1 | 19% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| Terminal-Bench 4.0 | 1.5% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| ProgramBench Almost@1 | 12.5% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| MiMo Code Bench (Xiaomi internal) | 40.4% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GraphWalks BFS 1M (F1) | 37% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Context: 1048576 |
| GraphWalks parents 1M (F1) | 62% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Context: 1048576 |
| GraphWalks BFS 512k (F1) | 56% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Context: 524288 |
| GraphWalks parents 512k (F1) | 92% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Context: 524288 |
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CyberGym | 40% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| ExploitBench | 16.6% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| ExploitGym | 0.2% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| SEC-Bench Pro | 17.7% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| MiMo Cyber Bench (Xiaomi internal) | 0% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Agents' Last Exam (pass rate) | 13.2% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
| Toolathlon Verified | 49.1% | Xiaomi, Xiaomi MiMo-V2.6-Pro-RL model cardchecked 2026-10-19 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Cost per taskVals AI, USD, lower is better | $0.17 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27 | Harness: OpenHands |
More from Xiaomi
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.