- HLE w. tool (acc) 47.2% (text-only 49.7%) 47.2
- BrowseComp (acc) 75.8
- deepsearchQA (F1), acc 81.7 92.8
- ResearchRubrics (score) 71.7
- Toolathlon (internal fixed version) 49.5
- Claweval-v1.1 (pass^3) 67.1
- GDPval-Stirrup 1415.8 (ii 45.8%) 1415.8
- SWE-MTLG 72.4
- SWE-Bench Pro 56.3
- SWE-Bench Verified 76.5
- Terminal-Bench 2.1 59.6
- AA-LCR (avg@16/acc) 63.9
- SimpleVQA (with search) 79.2
- WorldVQA 58.1
- BC-VL 59
- V* (with Python) 95.3
- Mean of HR-Bench 4K 89.13 / HR-Bench 8K 86.34 (with Python) 87.7
- VisualProbe (with Python) 65
- Score of Android Daily Benchmark 61.9
- Step-SWE-Bench avg over six harnesses 67.1
Step 3.7 Flash
Step 3.7 Flash places in the top three on 5 benchmarks.
StepFun Released 29 May 2026 32
Benchmarks with a score
0
Ranked first, out of five or more models
5
In the top three
StepFun May 2026 Step 3.7 Flash
Open weights
No Epoch Capabilities Index score yet
- AA-LCR (Artificial Analysis Long Context Reasoning) 63.9% #17 /31
- SimpleVQA 79.2% #2 /23
- Claw-Eval 80.5% #3 /23
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SimpleVQA | 79.2% | #2 of 23 | Model card | |
| Humanity's Last Exam | 47.2% | #47 of 147 | Model card | |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 63.9% | #17 of 31 | Model card | |
| Extended NYT Connections | 39.7% | #70 of 97 | Official leaderboard | |
| Judgemark v4 | 28.1 | #36 of 40 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MathArena (Apex, IMO, USAMO) | 14.6% | #17 of 47 | Official leaderboard | |
| CritPt | 2.29% | #83 of 160 | Epoch AI | |
| HMMT 2026 | 87.9% | #18 of 31 | Official leaderboard | |
| AIME 2026 | 95% | #19 of 31 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 76.5% | #37 of 150 | Model card | |
| SWE-bench Multilingual | 72.4% | #37 of 70 | Model card | |
| SWE-Bench Pro | 56.3% | #41 of 77 | Model card | |
| ALE-Bench | 694 | #82 of 121 | Epoch AI | |
| Monthly-SWEBench | 22% | #12 of 12 | Official leaderboard | |
| Step-SWE-Bench | 67.1% | #1 of 1 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Claw-Eval Pass^3 | 68.3% | #2 of 23 | Official leaderboard | |
| Claw-Eval | 80.5% | #3 of 23 | Official leaderboard | |
| DeepSearchQA | 92.8% | #4 of 22 | Model card | |
| ResearchRubrics | 71.7% | #2 of 5 | Model card | |
| AndroidDaily | 61.9% | #1 of 2 | Model card | |
| BrowseComp-VL | 59% | #1 of 2 | Model card | |
| BrowseComp | 75.8% | #39 of 77 | Model card | |
| Toolathlon | 49.5% | #21 of 37 | Model card | |
| SnakeBench | 21 | #114 of 183 | Official leaderboard | |
| PACT | 1,500 | #19 of 26 | Official leaderboard | |
| Terminal-Bench 2.1 | 59.6% | #43 of 53 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GDPval-AA | 1,416 | #12 of 16 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WorldVQA | 58.1% | #2 of 9 | Model card | |
| V* | 95.3% | #4 of 12 | Model card | |
| HR-Bench | 87.7% | #2 of 2 | Model card | |
| VisualProbe | 65% | #1 of 1 | Model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SuperCLUE | 48.2 | #18 of 18 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.