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.
Baidu · Pending · bench-align-v5
ERNIE 5.5 Flash Preview by Baidu carries a context window of 1M 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.
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.
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.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| HLE w/o tools Humanity's Last Exam without tools | 46.4 | #16 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ProgramBench ProgramBench: Can Language Models Rebuild Programs From Scratch? | 29.5 | #14 | 200 program reconstruction tasks | Full-repository software architecture | ProgramBench: Can Language Models Rebuild Programs From Scratch? |
| NL2Repo NL2Repo | 64.8 | #2 | Natural language to repository tasks | System-level software comprehension | MiniMax M2.7: Early Echoes of Self-Evolution |
| DeepSWE DeepSWE | 71.2 | #23 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| DRACO Data Research and Analysis with Complex Operations | 84.9 | #7 | Agentic data research and analysis tasks | Professional data analysis | Claude Opus 5 System Card |
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 46.50 | #14 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.0 |
| Terminal-Bench-Science 0.1 Terminal-Bench-Science 0.1 | 21.0 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| OfficeQA Pro v2 OfficeQA Pro v2 | 67.9 | #1 | Document and spreadsheet tasks | Enterprise document reasoning | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Cookie-Bench Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation | 88.2 | #4 | 1,000 web development queries (React setting) | Interactive web apps and static pages across three tiers | Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation |
| BlenderWorld (text-only) BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References (text-only subset) | 79.0 | #4 | 78 text-brief 3D creation tasks in Blender | Long-horizon 3D modeling and scene building | BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References |
| #13 |
| 70 expert-curated scientific research workflows |
| Frontier scientific research workflows |
| Terminal-Bench-Science 0.1 |
| BrowseComp BrowseComp | 87.4 | #15 | Research questions requiring browsing | Hard web research | BrowseComp |
| MCP Atlas MCP Atlas | 84.6 | #6 | Tool-integrated agent tasks | Advanced tool use | Introducing GPT-5.4 mini and nano |
| Toolathlon-Verified Toolathlon-Verified | 75.0 | #7 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| AutomationBench AutomationBench | 61.9 | #2 | 600 public automation tasks | Long-horizon automation | Kimi K3: Open Frontier Intelligence |
| APEX-Agents APEX-Agents | 64.2 | #3 | Professional-services agent tasks | Long-horizon professional work | Kimi K3: Open Frontier Intelligence |
| SpreadsheetBench 2 SpreadsheetBench 2 | 36.4 | #1 | Spreadsheet analysis and editing tasks | Professional spreadsheet work | Kimi K3: Open Frontier Intelligence |
| Agents' Last Exam (CLI) Agents' Last Exam v1.1, CLI subset | 29.0 | #2 | 86 CLI agent tasks | Advanced agentic work | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |