Benchmarks3mo ago
Qwen3.5 - GAIA
GAIA score 32.6 from TJ-0405
View sourceQwen
Qwen3.5-2B is a open-weight Qwen specialized model.
Running this yourself: can likely run on your own machine.
49.2
Quality Score
---
Arena ELO
2B
Parameters
---
Context
Sign in to join the discussion
1.4M
Downloads
227
Likes
Feb 2026
Released
Benchmarks
4
Open Source
1
Research
3
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
GAIA score 32.6 from TJ-0405
View sourceSWE-Bench Verified resolved rate 69.6
View sourceSWE-Bench Verified resolved rate 69.6
GAIA score 44.2 from WA0824
View sourceQwen3.5-2B is now available through local Ollama runtime. 256K context window listed. Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
View sourceHybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality against inference cost. However, existing methods for adaptive thinking-mode selection are typically evaluated under different models, datasets, and implementation assumptions, making it difficult to compare their practical behavior. We introduce HRBench, a unified evaluation framework for studying thinking-mode switching in hybrid-reasoning LLMs. HRBench organizes the design space along two axes: three switching strategy families, prompt-based selection, external routing, and speculative execution, and four training regimes, training-free, SFT, offline and online RL, yielding 12 controlled evaluation settings. We evaluate these settings across 6 LLMs, from Qwen3.5-2B to Kimi-K2.5-1.1T, and 5 reasoning benchmarks covering mathematics, science, and code, while reimplementing 12+ representative prior methods within the same pipeline. Our analysis characterizes how different switching strategies occupy distinct effectiveness-efficiency trade-off regions: prompt-based methods often provide favorable token-accuracy trade-offs, routing methods offer more stable cost reduction, and speculative methods tend to improve accuracy at higher token cost. We further find that training affects strategies differently, and that the preferred strategy varies with model scale and task domain. HRBench provides reference implementations and a unified evaluation platform to support more controlled research on efficient reasoning in hybrid-reasoning LLMs. Our data, code and repository are available at https://github.com/usail-hkust/HRBench.
Standard LLM benchmarks evaluate the assistant turn: the model generates a response to an input, a verifier scores correctness, and the analysis ends. This paradigm leaves unmeasured whether the LLM encodes any awareness of what follows the assistant response. We propose user-turn generation as a probe of this gap: given a conversation context of user query and assistant response, we let a model generate under the user role. If the model's weights encode interaction awareness, the generated user turn will be a grounded follow-up that reacts to the preceding context. Through experiments across 11 open-weight LLMs (Qwen3.5, gpt-oss, GLM) and 5 datasets (math reasoning, instruction following, conversation), we show that interaction awareness is decoupled from task accuracy. In particular, within the Qwen3.5 family, GSM8K accuracy scales from 41% (0.8B) to 96.8% (397B-A17B), yet genuine follow-up rates under deterministic generation remain near zero. In contrast, higher temperature sampling reveals interaction awareness is latent with follow up rates reaching 22%. Controlled perturbations validate that the proposed probe measures a real property of the model, and collaboration-oriented post-training on Qwen3.5-2B demonstrates an increase in follow-up rates. Our results show that user-turn generation captures a dimension of LLM behavior, interaction awareness, that is unexplored and invisible with current assistant-only benchmarks.
Autoformalization - automatically translating natural language mathematical texts into formal proof language such as Lean4 - can help accelerate AI-assisted mathematical research, be it via proof verification or proof search. I fine-tune Qwen3.5-2B with LoRA for natural language to Lean4 formalization on FineLeanCorpus and consider three training regimes: supervised fine-tuning (SFT) with curriculum learning (difficulty 1 to 10), SFT without curriculum ordering, and reinforcement learning using group relative policy optimization (GRPO) with a cycle consistency reward. Cycle consistency measures how well the meaning of a statement is preserved through a NL to Lean4 to NL' loop, computed as cosine similarity of off-the-shelf sentence embeddings. On an unseen subset of FineLeanCorpus (FLC) and on PutnamBench, RL substantially outperforms both SFT variants (mean cycle consistency 0.669 vs. 0.513 on FLC; 0.561 vs. 0.422 on PutnamBench), while increasing cross-entropy loss by only 0.011 nats, with minimal impact on formalization quality. Curriculum ordering provides no measurable benefit over shuffled training.
Qwen3.5-2B is now available through local Ollama runtime. 256K context window listed. Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
SWE-Bench Verified resolved rate 69.6
SWE-Bench Verified resolved rate 69.6