← Back to all development cases
This case was judged by an anonymized AI reviewer and has not been independently reviewed by people; inspect the draft, cards, and both outputs to assess it.
AutocompleteWith cards better262 / 280 · beu-fa1a1ff31a4f03b5

Qwen3 Technical Report

Computer science · 2505.09388v1

FLOWING EVIDENCE BENCHMARK

How do we compare writing with and without cards?

At the same writing position, the same model produces one first result with cards and one without. All 280 pairs enter the overall anonymized review, which assesses whether a decision not to continue fits the draft.

Overall: 138 with-card wins, 26 ties, 107 no-card wins, 5 pairs where neither was usable, and 4 inconclusive judgments. Both sides wrote text in 218 pairs; 48 had a deliberate stop and 14 included an invalid output.

SAME DRAFT · WITH OR WITHOUT CARDS

01 · FIXED WRITING POSITION

MANUSCRIPT

Same writing position ▌

Matched autocomplete at the same draft position

02 · TWO MATCHED VERSIONS

SHARED BY BOTH

Draft, writing task, and generation model

A · With cards

Relevant literature cards supplied

B · Without cards

No literature cards supplied

Generation model

Same model and version

A → first output

B → first output

Anonymized AI judge

First outputs are anonymized as X and Y

Continuation review: accuracy, fit to the writing task and usability
Returns: X preferred / tie / Y preferred / both unusable

Review again with the answer order swapped

HOW DOES BLIND JUDGING WORK?

① Anonymize both outputs
The AI judge sees the same draft and both first outputs without knowing which received cards.

② Compare and swap order
The judge applies task-specific criteria in X/Y and then Y/X order.

③ Review disagreements
A third pass resolves disagreements. Incomplete reviews remain in the denominator.

How are positions and cards selected?

We selected 40 writing positions in each of seven fields, for 280 comparisons. The position and relevant literature cards were set before each comparison, so both versions began from the same draft.

The main result retains every frozen position, including places where cards might not add a useful next move. This avoids selecting cases based on their outputs, but 49% describes the whole cohort, not a win rate where evidence clearly had an opportunity to help. This cohort did not record that opportunity label for each position before generation, so those two groups cannot yet be separated reliably.

CARD USE · 140/280

Reported card use in continuations with text

The model reports whether a card affected its continuation. In 140 of 280 tests it produced continuation text and reported card use. The previous count of 150 included 10 cases without continuation text and has been corrected.

COMPARISON · 70 / 7 / 30

Which written version was better?

Of the 107 reported-use cases where both versions produced text, the blinded AI judge preferred the with-card version 70 times, found 7 about the same, and preferred the without-card version 30 times.

How are the two table percentages calculated?

ADOPTION COVERAGE

140reported use with text
÷
280all positions
=
50%

WITH-CARD VERSION PREFERRED

70with cards better
÷
107comparable tests
=
65%

The percentages use different groups: 50% counts continuations with text reporting card use among all 280 tests; 65% covers the 107 such cases with text on both sides. The generating model reports card use, while an anonymized AI judge compares writing quality.

Card use is self-reported by the generator. The anonymized AI judge sees the draft and source snippets, so source-aware preference remains possible; there was no independent human review. The overall result describes these 280 frozen positions, not a win probability for any writing task.

Manuscript writing position

Text excerpt · not a PDF page

Research manuscript · excerpt

Qwen3 Technical Report

Introduction / methods

the flagship model Qwen3-235B-A22B achieves 85.7 on AIME’24 2

and 81.5 on AIME’25 (AIME, 2025), 70.7 on LiveCodeBench v5 (Jain et al., 2024), 2,056 on CodeForces, and 70.8 on BFCL v3 (Yan et al., 2024). In addition, other models in the Qwen3 series also show strong performance relative to their size. Furthermore, we observe that increasing the thinking budget for thinking tokens leads to a consistent improvement in the model’s performance across various tasks. In the following sections, we describe the design of the model architecture, provide details on its training procedures, present the experimental results of pre-trained and post-trained models, and finally, conclude this technical report by summarizing the key findings and outlining potential directions for future research. 2 Architecture The Qwen3 series includes 6 dense models, namely Qwen3-0.6B, Qwen3-1.7B, Qwen3-4B, Qwen3-8B, Qwen3-14B, and Qwen3-32B, and 2 MoE models, Qwen3-30B-A3B and Qwen3-235B-A22B. The flagship model, Qwen3-235B-A22B, has a total of 235B parameters with 22B activated ones. Below, we elaborate on the architecture of the Qwen3 models. The architecture of the Qwen3 dense models is similar to Qwen2.5

↓ Next paragraph was generated here

The highlighted text is near the writing position. This is a layout of the evaluation input, not a PDF screenshot.

A matched comparison at the same writing positionOverall AI review: With cards better

Both arms use the same model, task and manuscript context. Only the retrieved passages differ. The first recorded output from each arm is shown below.

Read overall AI review rationale

A = with cards · B = without cards

Both outputs attempt to continue the sentence comparing Qwen3 dense models to Qwen2.5. Output A provides specific, concrete architectural improvements (GQA, SwiGLU, RoPE, RMSNorm, pre-normalization) that are standard in modern LLM architectures and plausibly apply to Qwen models. These details fit the technical report genre and the context of elaborating on architecture. Output B is vague ('Qwen3-specific design choices') and adds no substantive information—it essentially says 'they differ in ways specific to Qwen3,' which is tautological and unhelpful. While B is not strictly invalid, it fails to advance the argument or provide the reader with any actual content. Output A is more useful, informative, and appropriate in scope for a technical report describing model architecture.

Evidence

Same model and position · retrieved passages supplied · first output

Preferred by blind review

models, incorporating improvements such as Grouped Query Attention (GQA), SwiGLU activation, Rotary Position Embeddings (RoPE), RMSNorm, and pre-normalization.

Passages supplied to the Evidence version

Card 1 · Qwen2.5 Technical Report

In this report, we introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been significantly improved during both the pre-training and post-training stages. In terms of pre-training, we have scaled the h…

Read full passage excerpt

In this report, we introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been significantly improved during both the pre-training and post-training stages. In terms of pre-training, we have scaled the high-quality pre-training datasets from the previous 7 trillion tokens to 18 trillion tokens. This provides a strong foundation for common sense, expert knowledge, and reasoning capabilities. In terms of post-training, we implement intricate supervised finetuning with over 1 million samples, as well as multistage reinforcement learning. Post-training techniques enhance human preference, and notably improve long text generation, structural data analysis, and instruction following. To handle diverse and varied use cases effectively, we present Qwen2.5 LLM series in rich sizes.

Card 2 · FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models

Recent research has demonstrated that Feed-Forward Networks (FFNs) in Large Language Models (LLMs) play a pivotal role in storing diverse linguistic and factual knowledge. Conventional methods frequently face challenges due to knowledge confusion stemming from their monolithic and redundant architec…

Read full passage excerpt

Recent research has demonstrated that Feed-Forward Networks (FFNs) in Large Language Models (LLMs) play a pivotal role in storing diverse linguistic and factual knowledge. Conventional methods frequently face challenges due to knowledge confusion stemming from their monolithic and redundant architectures, which calls for more efficient solutions with minimal computational overhead, particularly for LLMs. In this paper, we explore the FFN computation paradigm in LLMs and introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications, while maintaining the same level of performance. Furthermore, we embed a router from the Mixture-of-Experts (MoE), combined with our devised Prior-Approximate (PA) loss term that facilitates the dynamic activation of experts and knowledge adaptation, thereby accelerating computational processes and enhancing performance using minimal training data and fine-tuning steps. Fact …

Card 3 · ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained devices or efficiently serving them. Prior approaches have…

Read full passage excerpt

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained devices or efficiently serving them. Prior approaches have attempted to alleviate these problems by permanently removing less important model structures, yet these methods often result in substantial performance degradation due to the permanent deletion of model parameters. In this work, we tried to mitigate this issue by reducing the number of active parameters without permanently removing them. Specifically, we introduce a differentiable dynamic pruning method that pushes dense models to maintain a fixed number of active parameters by converting their MLP layers into a Mixture of Experts (MoE) architecture. Our method, even without fine-tuning, consistently outperforms previous structural pruning techniques across diverse model families, including …

Card 4 · FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models

Recent research has demonstrated that Feed-Forward Networks (FFNs) in Large Language Models (LLMs) play a pivotal role in storing diverse linguistic and factual knowledge. Conventional methods frequently face challenges due to knowledge confusion stemming from their monolithic and redundant architec…

Read full passage excerpt

Recent research has demonstrated that Feed-Forward Networks (FFNs) in Large Language Models (LLMs) play a pivotal role in storing diverse linguistic and factual knowledge. Conventional methods frequently face challenges due to knowledge confusion stemming from their monolithic and redundant architectures, which calls for more efficient solutions with minimal computational overhead, particularly for LLMs. In this paper, we explore the FFN computation paradigm in LLMs and introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications, while maintaining the same level of performance. Furthermore, we embed a router from the Mixture-of-Experts (MoE), combined with our devised Prior-Approximate (PA) loss term that facilitates the dynamic activation of experts and knowledge adaptation, thereby accelerating computational processes and enhancing performance using minimal training data and fine-tuning steps. Fact …

Card 5 · AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models

Mixture of experts (MoE) has become the standard for constructing production-level large language models (LLMs) due to its promise to boost model capacity without causing significant overheads. Nevertheless, existing MoE methods usually enforce a constant top-k routing for all tokens, which is argua…

Read full passage excerpt

Mixture of experts (MoE) has become the standard for constructing production-level large language models (LLMs) due to its promise to boost model capacity without causing significant overheads. Nevertheless, existing MoE methods usually enforce a constant top-k routing for all tokens, which is arguably restrictive because various tokens (e.g., "" vs. "apple") may require various numbers of experts for feature abstraction. Lifting such a constraint can help make the most of limited resources and unleash the potential of the model for downstream tasks. In this sense, we introduce AdaMoE to realize token-adaptive routing for MoE, where different tokens are permitted to select a various number of experts. AdaMoE makes minimal modifications to the vanilla MoE with top-k routing -- it simply introduces a fixed number of null experts, which do not consume any FLOPs, to the expert set and increases the value of k. AdaMoE does not force each token to occupy a fixed number of null experts but en …

Model-reported card use

The model did not report that any card materially affected this completion.

No Evidence

Same model and position · no retrieved passages · first output

Not preferred in this comparison

models, with the key difference being the use of Qwen3-specific design choices.

Earlier card-use comparison

The earlier diagnostic compared only cases with reported card use and text on both sides; its scope differs from the overall AI review above.

This case does not have both with-card continuation text and a model-reported use record. It remains among all 280 tests but does not enter the reported-use comparison.

The passages are input material; their presence does not mean an output used them or that they support every claim. Draft and source passages are excerpted; no simulated scores or PDF appear here.