We introduce Sage S2.1 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S2.1 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench 2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.
Figures & tables
Figure 1: Results on 15 selected benchmarks. Among the six compared models, Sage S2.1 Flash ranks first on four of these benchmarks and second on seven. Scores are displayed to one decimal place.
Figure 2: Overview of Sage S2.1 Flash . We use a shared language backbone that integrates text, images, and scientific inputs to support general-purpose and scientific tasks.
Figure 3: Overview of Sage Sci-Perception. Scientific inputs are encoded into local states and projected into continuous embeddings for the Sage S2.1 Flash model.
Figure 4: Overview of ToolSpace. A tool-centric framework for cross-environment data synthesis that improves long-horizon agentic tool use.
Source or material
Count
Notes
Kaggle sources
4,936
Deduplicated index: 2,660 dataset sources and 2,276 competition sources.
Hugging Face data entries
129
Public dataset candidates.
GitHub data releases
144
Public dataset candidates, rather than counts of retrieved code repositories.
Official sites and other open stores
427
Public dataset candidates.
Research papers
2,960
Entries in the checked input list.
Hugging Face base models
11
Model cards: 10 released and 1 quarantined.
Table 1: Sources and materials for task synthesis. Candidate inventory sizes do not represent counts of final training tasks.
Figure 5: Overview of the CUA training data construction pipeline of Sage S2.1 Flash: Real-world tasks are collected and scaled through seed-based task synthesis, followed by agent rollouts in interactive environments to generate execution trajectories, which are subsequently filtered through outcome verification and rejection sampling to obtain high-quality training data.
Benchmark
Sage S2.1 Flash
GLM-5.3- Flash
DeepSeek-V4.1- Flash-1017
Qwen3.8- Max
GPT-5.6 Sol
Claude Opus 5
GPT-6 Astra
GPT-6.1 Sol
Claude Opus 5.5
Agentic Coding
Terminal-Bench 2.1
87.9
84.3
87.6
89.6
86.2
90.2
87.4
–
87.6
DeepSWE
67.9
63.7
73.9
67.0
70.6
72.6
74.1
75.2
74.2
NL2Repo-Bench
57.2
53.0
62.7
63.2
60.7
79.9
–
–
–
SWE-bench Pro
60.6
60.3
61.8
65.3
59.8
76.5
–
–
89.9
Productivity
Table 2: Results across 33 benchmarks. Bold scores mark the best result among Sage S2.1 Flash and the five primary baselines. The three columns on the right reproduce published leading-model results. Dashes indicate unavailable scores.
Figure 6: Human-guided iterative trajectory analysis. Left: the coordinator verifies and pairs trajectories, schedules analysis, and retrieves requested tool calls, code changes, execution feedback, and artifacts. Lower center: the analyzer inspects records, requests evidence, and develops an explanation, which a separate invocation counterreviews; bidirectional arrows represent on-demand retrieval. Upper center: cycle synthesis proposes the next round’s case focus, evidence requests, and review criteria. Dashed elements denote proposals for subsequent analysis. Right: case findings retain evidence and interpretive limits for human review. The cycle supports both broader coverage of cases and questions and closer inspection of the evidence behind each explanation.
Figure 7: CT reconstruction: orientation matching, sequence recovery, and skeletal visualization in 3D Slicer.
Figure 8: Reference-guided architectural and mechanical modeling in Blender and CAD.
Figure 9: Scientific software workflows with visual checks of segmentation, signal processing, and water-area change.
Figure 10: The Memory of Light: three interactive views connecting physical parameters, simulated responses, and source literature.