# MAI-Image-2.5

> Source: Benchize (https://benchize.com) — https://benchize.com/models/mai-image-2-5. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/mai-image-2-5.

Microsoft

Canonical URL: https://benchize.com/models/mai-image-2-5
Last updated: Thu, 22 Oct 2026 05:30:58 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Microsoft

## Benchmarks

| Benchmark | Score | ± | Rank |  |
| --- | --- | --- | --- | --- |
| [Rapidata General image — coherence](https://benchize.com/benchmarks/rapidata%3Aimage%3Arlb_1PetHDuThgAvpj.md) | 972.88elo | CI 961.42–984.35 | 8 / 12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 972.8847262133877 \| elo \| rlb_1PetHDuThgAvpj \| Higher is better \| ### Configuration benchmarkId bmk_1Pet6iHzbf6RQu criterion rlb_1PetHDuThgAvpj participantId par_1PetshHzWmebbn sourceModelVersion MAI-Image 2.5 weighted false ### Reported statistics Uncertainty Confidence interval: 961.42–984.35 confidenceIntervalLowerOffset 11.46628272434873 confidenceIntervalUpperOffset 11.466282724348844 totalMatches 18734 wins 9063 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1Pet6iHzbf6RQu/standings/query?leaderboard_id%5Beq%5D=rlb_1PetHDuThgAvpj) Source rapidata Original model label MAI-Image 2.5 Source version v1 Observed 2026-10-21T16:37:27.701Z Evidence SHA-256 `4e459bb2e3b046f141fd621f02e8d8eab1bd23d4d9ec60b1ce76df04f7e117e6` Source locator `/items/30` |  |  |  |  |
| [Rapidata General image — Overall preference](https://benchize.com/benchmarks/rapidata%3Aimage%3Aoverall.md) | 1,029.73elo | CI 1,023.63–1,035.84 | 6 / 12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1029.7318165571423 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1Pet6iHzbf6RQu criterion overall participantId par_1PetshHzWmebbn sourceModelVersion MAI-Image 2.5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,023.63–1,035.84 confidenceIntervalLowerOffset 6.105306089050941 confidenceIntervalUpperOffset 6.105306089051055 totalMatches 65465.16250317052 wins 33656.86058150068 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1Pet6iHzbf6RQu/standings/query) Source rapidata Original model label MAI-Image 2.5 Source version v1 Observed 2026-10-21T16:37:24.778Z Evidence SHA-256 `eeb181d80ddb56c4d9473786d5a5a144381c0727bea85ccdc117c54899c53dfb` Source locator `/items/18` |  |  |  |  |
| [Rapidata General image — preference](https://benchize.com/benchmarks/rapidata%3Aimage%3Arlb_1Pf6xMzyixXVOB.md) | 1,098.03elo | CI 1,086.51–1,109.56 | 6 / 12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1098.0341550891737 \| elo \| rlb_1Pf6xMzyixXVOB \| Higher is better \| ### Configuration benchmarkId bmk_1Pet6iHzbf6RQu criterion rlb_1Pf6xMzyixXVOB participantId par_1PetshHzWmebbn sourceModelVersion MAI-Image 2.5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,086.51–1,109.56 confidenceIntervalLowerOffset 11.524919397557824 confidenceIntervalUpperOffset 11.524919397557824 totalMatches 18742 wins 10375 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1Pet6iHzbf6RQu/standings/query?leaderboard_id%5Beq%5D=rlb_1Pf6xMzyixXVOB) Source rapidata Original model label MAI-Image 2.5 Source version v1 Observed 2026-10-21T16:37:26.800Z Evidence SHA-256 `a6b4a9a60601efca881589c7ecde192803a23d60c6e324f0723bd407fd3b16a2` Source locator `/items/13` |  |  |  |  |
| [Rapidata General image — alignment](https://benchize.com/benchmarks/rapidata%3Aimage%3Arlb_1PetHDQclk27pp.md) | 1,048.15elo | CI 1,036.64–1,059.65 | 6 / 12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1048.1460439807342 \| elo \| rlb_1PetHDQclk27pp \| Higher is better \| ### Configuration benchmarkId bmk_1Pet6iHzbf6RQu criterion rlb_1PetHDQclk27pp participantId par_1PetshHzWmebbn sourceModelVersion MAI-Image 2.5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,036.64–1,059.65 confidenceIntervalLowerOffset 11.50641089229066 confidenceIntervalUpperOffset 11.50641089229066 totalMatches 18742 wins 9757.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1Pet6iHzbf6RQu/standings/query?leaderboard_id%5Beq%5D=rlb_1PetHDQclk27pp) Source rapidata Original model label MAI-Image 2.5 Source version v1 Observed 2026-10-21T16:37:26.126Z Evidence SHA-256 `08039e9908e5af4e993244cd4449bbd7f274ef5e68ad22ddcb80b3780bb89b6e` Source locator `/items/17` |  |  |  |  |
| [Rapidata General image — text coherence](https://benchize.com/benchmarks/rapidata%3Aimage%3Arlb_1RNU9vh78AqXX1.md) | 998.55elo | CI 982.7–1,014.4 | 9 / 12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 998.5471581615816 \| elo \| rlb_1RNU9vh78AqXX1 \| Higher is better \| ### Configuration benchmarkId bmk_1Pet6iHzbf6RQu criterion rlb_1RNU9vh78AqXX1 participantId par_1PetshHzWmebbn sourceModelVersion MAI-Image 2.5 weighted false ### Reported statistics Uncertainty Confidence interval: 982.7–1,014.4 confidenceIntervalLowerOffset 15.849217204409456 confidenceIntervalUpperOffset 15.849217204409456 totalMatches 9701 wins 4839 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1Pet6iHzbf6RQu/standings/query?leaderboard_id%5Beq%5D=rlb_1RNU9vh78AqXX1) Source rapidata Original model label MAI-Image 2.5 Source version v1 Observed 2026-10-21T16:37:28.390Z Evidence SHA-256 `3e902908fb67a7e7f6847c980214023674921887f6b58453fab8dd808b0c83ac` Source locator `/items/27` |  |  |  |  |

---
Cite as: MAI-Image-2.5 — Benchize, https://benchize.com/models/mai-image-2-5 (retrieved 2026-10-22)