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.
StepFun · Open Weight · rank 45 · bench-align-v5
Step 5 Preview is built for coding, agent work and reasoning. It ranks in the top quarter for reasoning (top 5% of 216 scored models) and coding (top 7% of 210 scored models), by BenchLM's published scores.
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.
Step 5 Preview by StepFun scores 62.7 overall, costs $1.00 per 1M input tokens and $2.70 per 1M output tokens, and 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.
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: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 29.6 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 138 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GPQA-D GPQA Diamond | 93.5 | #13 | Graduate-level science questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| HLE Humanity's Last Exam | 46.5 | #30 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 28.5 | #66 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-HLE Artificial Analysis Humanity's Last Exam | 46.5 | #23 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 16.4 | #41 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 36.4 | #75 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 31.3 | #185 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 85.0 | #20 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| ProgramBench ProgramBench: Can Language Models Rebuild Programs From Scratch? | 80.5 | #5 | 200 program reconstruction tasks | Full-repository software architecture | ProgramBench: Can Language Models Rebuild Programs From Scratch? |
| MLS-Bench Lite MLS-Bench Lite | 40.5 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 88.3 | #2 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 16.7 | #39 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 20.9 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| DRACO Data Research and Analysis with Complex Operations | 83.3 | #8 | Agentic data research and analysis tasks | Professional data analysis | Claude Opus 5 System Card |
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 33.30 | #23 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.0 |
| AA Briefcase Artificial Analysis Briefcase | 1424 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 76 | #34 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 76.4 | #46 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| OfficeQA Pro OfficeQA Pro | 60.3 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| NYT Connections NYT Connections LLM Benchmark (extended version) | 76.6 | #46 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | NYT Connections LLM Benchmark (Lech Mazur, GitHub) |
| StealthMark StealthMark Intelligence Benchmarks (overall score) | 39.0 | #32 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | StealthMark: The AI Benchmark Explained (Stealth Models) |
| HoneyBench HoneyBench v0.2 (Goodhart Labs) |
People's votes between two anonymous answers on arena.ai, one board per task. LMArena's own ratings and ranks, one line per model version it rates; not part of this site's capability scores or rank.
| Board | Variant | Rating | Votes | Rank | Published | Evidence |
|---|---|---|---|---|---|---|
| Vision Arena People's votes between two answers about the same image, style-controlled. | — | 1,247 ± 10 | 4,395 | 60 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #3 |
| 30 machine-learning research tasks |
| ML research and systems engineering |
| MLS-Bench |
| SciCode Scientific Code Benchmark | 58.9 | #2 | — | — | BenchLM |
| AA-SciCode Artificial Analysis SciCode | 58.9 | #13 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| DeepSWE DeepSWE | 67.7 | #31 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| #26 |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| #33 |
| Professional knowledge-work tasks |
| Professional work |
| Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 51.0 | #35 | Business-process automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| AA EnterpriseOps-Gym Artificial Analysis EnterpriseOps-Gym | 47.2 | #9 | Enterprise operations workflows | Enterprise agent operations | Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard |
| AA Harvey LAB v1.0 Artificial Analysis Harvey LAB-AA v1.0 | 93.4 | #4 | Legal agent tasks | Professional legal work | Artificial Analysis Harvey LAB-AA Benchmark Leaderboard |
| AA ITBench Artificial Analysis ITBench-AA | 55.6 | #2 | IT incident-response tasks | Enterprise IT operations | Artificial Analysis ITBench-AA Benchmark Leaderboard |
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 85.0 | #21 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| BrowseComp BrowseComp | 88.7 | #12 | Research questions requiring browsing | Hard web research | BrowseComp |
| GDPval-AA GDPval-AA | 1566 | #36 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 54.3 | #25 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 33.3 | #26 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 14.8 | #39 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 35.0 | #32 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| APEX-Agents-AA APEX-Agents-AA | 38.0 | #6 | 452 professional-services agent tasks | Long-horizon workplace agent tasks | APEX-Agents-AA Benchmark Leaderboard |
| CyberGym CyberGym | 84.7 | #8 | 1,507 vulnerability analysis instances | Real-world cybersecurity | CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale |
| JobBench JobBench | 59.0 | #11 | 130 tasks across 35 occupations | Professional multi-source workflows | JobBench: Aligning Agent Work With Human Will |
| MCP Atlas MCP Atlas | 85.6 | #4 | Tool-integrated agent tasks | Advanced tool use | Introducing GPT-5.4 mini and nano |
| Toolathlon-Verified Toolathlon-Verified | 74.1 | #8 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| AutomationBench AutomationBench | 44.0 | #18 | 600 public automation tasks | Long-horizon automation | Kimi K3: Open Frontier Intelligence |
| Agents' Last Exam Agents' Last Exam | 29.5 | #14 | Agent tasks | Advanced agentic work | DeepSeek V4 Flash 0731 update |
| APEX-Agents APEX-Agents | 37.8 | #7 | Professional-services agent tasks | Long-horizon professional work | Kimi K3: Open Frontier Intelligence |
| Hermes Index Hermes Index: agentic capability and cost per task inside Hermes Agent | 32.8 | #16 | Four suites: Hermes Bench (150 tasks), TerminalBench 4 without its 4 GPU tasks, TerminalBench Science and SkillsBench | Frontier agentic | Hermes Index: an agentic model leaderboard |
| Hermes Bench Hermes Bench: 150 agent tasks graded on the files and state the agent leaves behind | 69.2 | #14 | 150 tasks across 25 categories | Frontier agentic | Hermes Bench (Hermes Index) |
| AA Cyber Index Artificial Analysis Cyber Index | 47.7 | #7 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | Artificial Analysis Cyber Index |
| CWE-Bench-AA Artificial Analysis CWE-Bench-AA | 52.5 | #15 | Real-world vulnerability patching tasks | Automated vulnerability remediation | CWE-Bench-AA Benchmark Leaderboard |
| DeepsecBench-AA Artificial Analysis DeepsecBench-AA | 15.8 | #16 | Vulnerability discovery in real codebases | Security code review | DeepsecBench-AA Benchmark Leaderboard |
| CyberGym-E2E-AA Artificial Analysis CyberGym-E2E-AA | 74.8 | #5 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | CyberGym-E2E-AA Benchmark Leaderboard |
| MKA Multimodal Knowledge Agent Benchmark | 27.6 | #22 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | MKA Benchmark Leaderboard |
| #11 |
| Document and spreadsheet tasks |
| Enterprise grounded reasoning |
| OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning |
| 64.9 |
| #13 |
| 20 private honeypot tasks across 7 domains with exploitable evaluators |
| Agentic alignment and specification gaming |
| HoneyBench v0.2 |