# Mistral Medium 3

> Source: Benchize (https://benchize.com) — https://benchize.com/models/mistral-medium-3. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/mistral-medium-3.

Mistral AI

Canonical URL: https://benchize.com/models/mistral-medium-3
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.

Mistral AI

## Benchmarks

| Benchmark | Score | ± | Rank | Source |  |
| --- | --- | --- | --- | --- | --- |
| [Humanity’s Last Exam (HLE)](https://benchize.com/benchmarks/hle.md) | 4.52source score | CI 3.71–5.33 | 17 / 17 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 4.52 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Mistral Medium 3 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 3.71–5.33 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 51 reportedConfidenceHalfWidth 0.81 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam) Source scale Original model label Mistral Medium 3 Observed 2026-10-22T03:30:08.991Z Evidence SHA-256 `2e7bc7983b3fe2fab5270a4dc00f51a40b87f5318a686fbae4291beda672f604` Source locator `/rows/50` |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 58.53% | — | 30 / 39 | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 58.53 \| percent \| overall \| Higher is better \| \| `stability` \| 0.496 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.621 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.533 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion mistral-medium-3 ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label mistral-medium-3 Source version judgemark-v2 Observed 2026-10-22T05:10:06.632Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/18` |  |  |  |  |  |
| [MASK](https://benchize.com/benchmarks/scale%3Amask.md) | 42.6source score | CI 39.34–45.86 | 24 / 25 | [scale](https://labs.scale.com/leaderboard/mask) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 42.6 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Mistral Medium 3 sourceModelVersion mistral-medium-latest thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 39.34–45.86 contaminationWarning Not reported rank 65 reportedConfidenceHalfWidth 3.26 ### Source [Original source](https://labs.scale.com/leaderboard/mask) Source scale Original model label Mistral Medium 3 Observed 2026-10-22T03:30:12.706Z Evidence SHA-256 `fe1699303dff9a092aff10128cfc39d63ddc0680c0d241345fa747c450597b67` Source locator `/rows/64` |  |  |  |  |  |
| [VISTA](https://benchize.com/benchmarks/scale%3Avisual_language_understanding.md) | 34.59source score | CI 33.47–35.71 | 12 / 16 | [scale](https://labs.scale.com/leaderboard/visual_language_understanding) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 34.59 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Mistral Medium 3 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 33.47–35.71 contaminationWarning Not reported rank 51 reportedConfidenceHalfWidth 1.12 ### Source [Original source](https://labs.scale.com/leaderboard/visual_language_understanding) Source scale Original model label Mistral Medium 3 Observed 2026-10-22T03:30:13.295Z Evidence SHA-256 `d373f192d42603b3d2b7b0b509c801be37a4fd65b7c73742f980d9f2f0a4e668` Source locator `/rows/50` |  |  |  |  |  |
| [Humanity's Last Exam (Text Only)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_text_only.md) | 4.36source score | CI 3.5–5.22 | 25 / 25 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 4.36 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Mistral Medium 3 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 3.5–5.22 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. Sampled at temperature 0.3. rank 61 reportedConfidenceHalfWidth 0.86 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) Source scale Original model label Mistral Medium 3 Observed 2026-10-22T03:30:09.372Z Evidence SHA-256 `16bd91dbd41a73afd31ff09fba3b9b08e9e3e2cfe682c50cc3b2bf8397610af6` Source locator `/rows/60` |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,283 | — | 164 / 191 | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1283 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_mistralai_mistral_medium_3 ### Reported statistics coverageCount 27 draws 0 judged 23 losses 18 rank 262 ratingDeviation 28 wins 5 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Mistral Medium 3 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/246` |  |  |  |  |  |

---
Cite as: Mistral Medium 3 — Benchize, https://benchize.com/models/mistral-medium-3 (retrieved 2026-10-22)