What are Step3 VL 10B's benchmark scores?

As of 24 Oct 2026, Step3 VL 10B scores 42.4 ±6.1 on the BenchLeader Index, strongest in instruction following (52) and weakest in long context (23). That rests on 7 independent benchmark results, and every score on this page links to its publisher.

How does Step3 VL 10B rank?

Step3 VL 10B is #597 of 785 ranked configurations on 24 Oct 2026. 344 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 Step3 VL 10B released?

StepFun released Step3 VL 10B on 20 Jan 2026.

StepFun Open weights: stepfun-ai/Step3-VL-10BReasoning modelCompare with another model

Step3 VL 10B

Step3 VL 10B is a StepFun open-weights reasoning model, released 20 Jan 2026. Its best configuration ranks #597 of 785 on the BenchLeader Index at 42.4 ±6.1, in the lower half. The ± is the point: 344 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 instruction following (52) and lowest in long context (23). Last measured 20 Jan 2026.stale: no new result in six months

Blended price: –
Output speed: –
First answer: –
Context: 66k
Full answer: –
Cost per run: –
Released: 20 Jan 2026

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

Overall index42
Reasoning41
Agents & tools38
Knowledge35
Instruction following52
Multimodal47
Long context23
Composite38

How its index has moved

9 Sept 2026 to 21 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	not stated	Source
GPQA Diamond (AA)not in index	69.0%#308	Artificial Analysis
Humanity's Last Exam (AA)not in index	10.8%#309	Artificial Analysis
CritPt	0.0%#315	Artificial Analysis

Agents & tools

Benchmark	not stated	Source
Terminal-Bench Hard	5.3%#277	Artificial Analysis
τ²-Bench Telecom (AA)not in index	16.1%#357	Artificial Analysis

Knowledge

Benchmark	not stated	Source
AA-Omniscience	-59#457	Artificial Analysis
AA-Omniscience: accuracynot in index	13.3%#459	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	16.7%#325	Artificial Analysis

Instruction following

Benchmark	not stated	Source
IFBench	50.2%#174	Artificial Analysis

Multimodal

Benchmark	not stated	Source
MMMU-Pro	64.0%#187	Artificial Analysis

Long context

Benchmark	not stated	Source
AA-LCR	0.0%#493	Artificial Analysis

Composite

Benchmark	not stated	Source
AA Intelligence Index v4.3.2	7.7#461	Artificial Analysis

New this month

Questions people ask

What are Step3 VL 10B's benchmark scores?: As of 24 Oct 2026, Step3 VL 10B scores 42.4 ±6.1 on the BenchLeader Index, strongest in instruction following (52) and weakest in long context (23). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
How does Step3 VL 10B rank?: Step3 VL 10B is #597 of 785 ranked configurations on 24 Oct 2026. 344 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 Step3 VL 10B released?: StepFun released Step3 VL 10B on 20 Jan 2026.

Data as of 24 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Step3 VL 10B: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/step-3-vl-10b.