Qwen3.5 - GAIA
GAIA score 32.6 from TJ-0405
View sourceQwen
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.
Running this yourself: can likely run on your own machine.
Live access is not confirmed for this model. No current purchase price is advertised.
No current subscription pricing is tracked for this model.
Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.
No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.
55.2
Quality Score
---
Arena ELO
2B
Parameters
262K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
20 of 22 public signals
Sign in to join the discussion
5.5M
Downloads
490
Likes
Feb 2026
Released
5/5 signals
3/4 signals
4/5 signals
4/4 signals
4/4 signals
Parameters
2B
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Source-reported access: Open weights (restricted use) · Confident confidence
Gaps we are still tracking
Benchmarks
6
Open Source
1
Research
5
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
Qwen published benchmark or leaderboard evidence for Qwen3.5-2B.
View sourceGAIA score 44.2 from WA0824
View sourceWeight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning loops of Qwen3.5-0.8B without gradients, using 158 agent turns, 89.7 million tokens, and 50 forward-pass requests. Our method, Tree-Ising, casts this repair as a sparse discrete optimization problem over the model's own BF16 weights. Forward statistics define an objective that weakens a loop direction, strengthens a concluding direction, and preserves the layer's output on productive tokens. Within a state-tree representation, where lossless BF16 storage acts as a special case, the admissible edits are sign flips and exponent shifts that preserve all shared group exponents and mantissas. We decompose this objective exactly into independent QUBO (Ising) problems, one per output row, which we solve on a GPU using simulated annealing or quantum-inspired simulated bifurcation. On the agent's two layers, Tree-Ising achieves 54.6% on MATH-500, outperforming the agent's edit (51.7%) under the same evaluation protocol, while the base model scores 7.9% as reported. The simulated bifurcation solver yields a statistically indistinguishable repair at 55.1%. Both solvers outperform the agent edit across all five math benchmarks, with statistically significant improvements on MATH-500 and GSM8K after correcting for multiple comparisons. Our approach modifies 13% to 17% fewer weights and reduces BF16 bit flips by a factor of 2.2 to 2.3. It requires only four forward-pass requests and zero LLM tokens, with the annealing recipe costing about $0.90 in GPU time. On Qwen3.5-2B, with layers and dose selected using only the base model, the same recipe increases greedy GSM8K accuracy from 21.6% to 69.4%. As a proof of concept, we execute an eight-variable repair subproblem using QAOA on an IBM Heron processor.
A spectrum can be given to a model as a table in nanometers or as a plot in photon energy, and the decision should not depend on which one it sees. When the data needed for an answer are missing, the model should say so. We test representation invariance and abstention on measured optical spectra of silicon metasurfaces (MOCLIP) and gold nanoparticles, with labels computed from the data. Each spectrum is shown as four tables (nm, μm, scientific notation, eV) and two plots (nm, eV), and partial spectra remove data inside or outside the queried range. We evaluate the decision models d3-nano and Jev 1.13, three GPT-6 Luna configurations and the Qwen3.5-2B base model. Changing only the representation moves accuracy by up to 41 percentage points within one model, mostly on photon-energy tables and plots. With the same evidence, asking in photon energy instead of wavelength helps some model-view pairs by 16-50 points and hurts others by up to 25. When the relevant extremum is removed, unadapted models rarely answer "undetermined". LoRA fine-tuning of d3-nano improves comparisons on the trained table formats, but much of its gain on unanswerable questions comes from a shortcut: it abstains whenever the input is truncated. Training with answerable truncations avoids the shortcut in all six seeds, with a 90-100 point gap between abstention after inside and outside cuts on held-out structures; with the same amount of extra original-task data, five of six seeds keep the shortcut. On gold spectra the two training sets perform similarly. Multimodal language models used for scientific decisions should be tested on equivalent representations and on missing evidence, not only on average accuracy. We release the tasks, per-response results and analysis code.
Hybrid-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. 40K context window listed. Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
SWE-Bench Verified resolved rate 69.6
SWE-Bench Verified resolved rate 69.6
Qwen published benchmark or leaderboard evidence for Qwen3.5-2B.