Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Dots Studio · Open Weight · rank 57 · bench-align-v5
dots3-note Preview is a general-purpose language model. It ranks in the top quarter for knowledge (top 18% of 284 scored models) and instruction following (top 19% of 159 scored models), by BenchLM's published scores.
dots3-note Preview by Dots Studio scores 59.9 overall and carries a context window of 512K tokens — observed 2026-11-21.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Every published price component, including cache reads and writes.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | Unavailable | Unavailable | Unavailable |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| HLE Humanity's Last Exam | 52.6 | #21 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 75.1 | #45 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| Codeforces Codeforces Rating | 3056.0 | #4 | Competitive programming contests | Elite competitive programming | DeepSeek-V4 Technical Report |
| SWE-bench Verified Software Engineering Benchmark Verified | 78.4 | #30 | 500 verified issues | Professional software engineering | SWE-bench: Can Language Models Resolve Real-World GitHub Issues? |
| LiveCodeBench v6 LiveCodeBench v6 | 91.5 | #7 | Fresh programming problems | Competitive programming level | LiveCodeBench official repository and release documentation |
| SWE-bench Pro SWE-bench Pro | 61 | #32 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| SWE Multilingual SWE Multilingual | 75.7 | #29 | Multilingual software-engineering tasks | Professional software engineering | MiniMax M2.7: Early Echoes of Self-Evolution |
| NL2Repo NL2Repo | 49.8 | #13 | Natural language to repository tasks | System-level software comprehension | MiniMax M2.7: Early Echoes of Self-Evolution |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| IMOAnswerBench IMOAnswerBench | 90.9 | #1 | Advanced mathematical answer generation | Olympiad-level mathematics | DeepSeek-V4 Technical Report |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ARC-AGI-2 Abstraction and Reasoning Corpus for AGI v2 | 81.4 | #20 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | ARC-AGI-2: A Harder General Intelligence Benchmark |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 75.1 | #47 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| BrowseComp BrowseComp | 83.3 | #25 | Research questions requiring browsing | Hard web research | BrowseComp |
| HLE w/ tools Humanity's Last Exam with tools | 52.6 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GDP.pdf (no tools) GDP.pdf mean criteria pass rate without tools | 60.7 | #3 | 100 professional document prompts | Professional document reasoning | GDP.pdf |
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 79.1 | #18 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| PerceptionBench PerceptionBench (Internal) | 53.4 |
| #25 |
| Expert questions with tool use |
| Frontier tool-augmented reasoning |
| DeepSeek-V4 Technical Report |
| Toolathlon-Verified Toolathlon-Verified | 55.6 | #20 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| APEX-Agents APEX-Agents | 30.8 | #10 | Professional-services agent tasks | Long-horizon professional work | Kimi K3: Open Frontier Intelligence |
| DeepSearchQA DeepSearchQA | 92.1 | #8 | Agentic browsing and list-answer questions | Agentic web research | Muse Spark Eval Methodology |
| Claw-Eval Claw-Eval | 73.4 | #6 | 300 tasks, 2,159 rubrics | Real-world general, multi-turn, and native multimodal agent execution | Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents |
| WideResearch WideResearch | 78.9 | #7 | Open-ended research tasks | Broad research-agent workflows | Qwen3.6 launch benchmarks |
| #6 |
| Internal atomic visual-perception tasks |
| Fine-grained visual perception |
| Kimi K3: Open Frontier Intelligence |
| MathVision MathVision | 87.7 | #13 | Visually grounded math problems | Advanced multimodal mathematics | Qwen3.6 launch benchmarks |
| VideoMMMU VideoMMMU | 86.8 | #3 | Video-grounded expert reasoning | Frontier multimodal video reasoning | Qwen3.6 launch benchmarks |
| MMVU Multimodal Multi-disciplinary Video Understanding | 79.9 | #4 | Video understanding | Multi-disciplinary multimodal video reasoning | Kimi K2.5 benchmark release surface |
| ZeroBench ZeroBench | 19.0 | #8 | 100 visual reasoning questions | Tool-augmented visual reasoning | Muse Spark Eval Methodology |
| SimpleVQA SimpleVQA | 72.5 | #6 | Visual QA tasks | General visual understanding | GLM-5V-Turbo |
| CharXiv w/o tools CharXiv Reasoning without tools | 83.1 | #11 | Scientific chart reasoning (tool-free) | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| BabyVision BabyVision | 50.0 | #10 | Visual perception tasks | Fine-grained visual perception | Muse Spark 1.1 Evaluation Report |