What are DeepSeek-R1-0528-Qwen3-8B's benchmark scores?

As of 24 Oct 2026, DeepSeek-R1-0528-Qwen3-8B scores 37.6 ±6.7 on the BenchLeader Index, strongest in maths (43) and weakest in instruction following (25). That rests on 8 independent benchmark results, and every score on this page links to its publisher.

How does DeepSeek-R1-0528-Qwen3-8B rank?

DeepSeek-R1-0528-Qwen3-8B is #728 of 785 ranked configurations on 24 Oct 2026. 249 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.

How much does DeepSeek-R1-0528-Qwen3-8B cost per 1M tokens?

As of 24 Oct 2026, DeepSeek-R1-0528-Qwen3-8B costs $0.060 per 1M input tokens and $0.090 per 1M output tokens, $0.068 blended (three input tokens per output token).

When was DeepSeek-R1-0528-Qwen3-8B released?

DeepSeek released DeepSeek-R1-0528-Qwen3-8B on 29 May 2025.

DeepSeek Open weights: deepseek-ai/DeepSeek-R1-0528-Qwen3-8BReasoning modelCompare with another model

DeepSeek-R1-0528-Qwen3-8B

DeepSeek-R1-0528-Qwen3-8B is a DeepSeek open-weights reasoning model, released 29 May 2025. Its best configuration ranks #728 of 785 on the BenchLeader Index at 37.6 ±6.7, in the lower half. The ± is the point: 249 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 maths (43) and lowest in instruction following (25). At $0.068 per million tokens blended it is among the cheapest fifth of ranked models. Last measured 29 May 2025.stale: no new result in six months

Blended price: $0.068/M; $0.060 in · $0.090 out
Output speed: –
First answer: –
Context: 128k
Full answer: –
Cost per run: –
Released: 29 May 2025

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

Overall index38
Reasoning26
Agents & tools35
Maths43
Knowledge33
Instruction following25
Long context31
Composite39

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	not stated	Source
GPQA Diamond	9.3%#293	Epoch AI Benchmarking Hub
GPQA Diamond (AA)not in index	61.2%#368	Artificial Analysis
Humanity's Last Exam (AA)not in index	5.9%#411	Artificial Analysis
CritPt	0.0%#315	Artificial Analysis

Agents & tools

Benchmark	not stated	Source
Terminal-Bench Hard	1.5%#338	Artificial Analysis
τ²-Bench Telecom (AA)not in index	0.0%#393	Artificial Analysis

Maths

Benchmark	not stated	Source
OTIS Mock AIME	43.9%#195	Epoch AI Benchmarking Hub

Knowledge

Benchmark	not stated	Source
AA-Omniscience	-63.6#489	Artificial Analysis
AA-Omniscience: accuracynot in index	12.2%#473	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	13.7%#357	Artificial Analysis

Instruction following

Benchmark	not stated	Source
IFBench	19.9%#417	Artificial Analysis

Long context

Benchmark	not stated	Source
AA-LCR	15.0%#454	Artificial Analysis

Composite

Benchmark	not stated	Source
AA Intelligence Index v4.3.2	8.1#446	Artificial Analysis

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

Workload	Tokens in / out	Cost	With caching	Time
Chat reply	400 / 300	$0.0001	–	–
Summarize a 30-page report	12,000 / 600	$0.0008	–	–
Code edit	6,000 / 1,500	$0.0005	–	–
Agentic coding session	60,000 / 4,000	$0.0040	–	–
Structured extraction	2,000 / 200	$0.0001	–	–

New this month

Questions people ask

What are DeepSeek-R1-0528-Qwen3-8B's benchmark scores?: As of 24 Oct 2026, DeepSeek-R1-0528-Qwen3-8B scores 37.6 ±6.7 on the BenchLeader Index, strongest in maths (43) and weakest in instruction following (25). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
How does DeepSeek-R1-0528-Qwen3-8B rank?: DeepSeek-R1-0528-Qwen3-8B is #728 of 785 ranked configurations on 24 Oct 2026. 249 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.
How much does DeepSeek-R1-0528-Qwen3-8B cost per 1M tokens?: As of 24 Oct 2026, DeepSeek-R1-0528-Qwen3-8B costs $0.060 per 1M input tokens and $0.090 per 1M output tokens, $0.068 blended (three input tokens per output token).
When was DeepSeek-R1-0528-Qwen3-8B released?: DeepSeek released DeepSeek-R1-0528-Qwen3-8B on 29 May 2025.

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

Cite as: BenchLeader, “DeepSeek-R1-0528-Qwen3-8B: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/deepseek-r1-0528-qwen3-8b.