What are Devstral Medium's benchmark scores?

As of 25 Oct 2026, Devstral Medium (medium effort) scores 39.8 ±7.2 on the BenchLeader Index, strongest in knowledge (47) and weakest in coding (11). That rests on 8 independent benchmark results, and every score on this page links to its publisher.

How does Devstral Medium rank?

Devstral Medium (medium effort) is #672 of 785 ranked configurations on 25 Oct 2026. 320 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Devstral Medium released?

Mistral AI released Devstral Medium on 10 Jul 2025.

Mistral AI Compare with another model

Devstral Medium

Devstral Medium is a Mistral AI proprietary model, released 10 Jul 2025. Its best configuration (medium reasoning effort) ranks #672 of 785 on the BenchLeader Index at 39.8 ±7.2, in the lower half. The ± is the point: 320 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in knowledge (47) and lowest in coding (11). Last measured 23 Oct 2026.

Blended price: –
Output speed: –
First answer: –
Context: 256k
Full answer: –
Cost per run: –
Released: 10 Jul 2025

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index40
Reasoning39
Coding11
Agents & tools42
Knowledge47
Instruction following34
Long context40
Composite40

How its index has moved

9 Sept 2026 to 23 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	medium	Source
GPQA Diamond (AA)not in index	49.2%#432	Artificial Analysis
Humanity's Last Exam (AA)not in index	3.8%#571	Artificial Analysis
Kagi LLM Benchmark	37.7%#112	Kagi LLM Benchmark
CritPt	0.0%#315	Artificial Analysis

Coding

Benchmark	medium	Source	Trend
Arena WebDev	1072#139	Arena (LMArena)

Agents & tools

Benchmark	medium	Source	Trend
Terminal-Bench Hard	9.1%#231	Artificial Analysis
τ²-Bench Telecom (AA)not in index	19.9%#335	Artificial Analysis

Knowledge

Benchmark	medium	Source
AA-Omniscience	-31.6#287	Artificial Analysis
AA-Omniscience: accuracynot in index	18.9%#325	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	37.8%#173	Artificial Analysis

Instruction following

Benchmark	medium	Source	Trend
IFBench	29.9%#365	Artificial Analysis

Long context

Benchmark	medium	Source	Trend
AA-LCR	32.0%#387	Artificial Analysis

Composite

Benchmark	medium	Source	Trend
AA Intelligence Index v4.3.2	9.0#414	Artificial Analysis

New this month

Questions people ask

What are Devstral Medium's benchmark scores?: As of 25 Oct 2026, Devstral Medium (medium effort) scores 39.8 ±7.2 on the BenchLeader Index, strongest in knowledge (47) and weakest in coding (11). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
How does Devstral Medium rank?: Devstral Medium (medium effort) is #672 of 785 ranked configurations on 25 Oct 2026. 320 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Devstral Medium released?: Mistral AI released Devstral Medium on 10 Jul 2025.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Devstral Medium: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/devstral-medium.