Step 3.7 Flash: benchmark results
StepFun's speed-oriented Step 3.7 Flash model. Provider: StepFun. Released 2026-05-29. Access: Open.
Aggregate Rating 1684 ± 10, rank #236 of 1656 rated models, from 189 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Tau2-Bench Telecom | 98.54 | Success Rate (%) | 99.2 |
| AA TAU-2 Bench | 98.54 | Accuracy (%) | 99 |
| ReferFlow-Bench - Shift - F-Acc | 45.1 | F-Acc (%) | 95.7 |
| ReLE - Agents - BFCL-V3 | 72.3 | Accuracy (%) | 94.2 |
| ReLE - Agents and Tool Use | 69.9 | Accuracy (%) | 93.6 |
| AA Omniscience - Software Engineering (SWE) - Rust | 70 | Accuracy (%) | 92.2 |
| CLAW-Eval | 80.5 | Score (%) | 92 |
| AA Omniscience - Software Engineering (SWE) - Julia | 32 | Accuracy (%) | 90.1 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 34 | Accuracy (%) | 88.1 |
| AA Omniscience - Software Engineering (SWE) - HTML | 50 | Accuracy (%) | 87.7 |
| ReferFlow-Bench - Refinement - T-Acc | 10.2 | T-Acc (%) | 87 |
| ReferFlow-Bench - Shift - T-Acc | 22.3 | T-Acc (%) | 87 |
Interactive version: theaggregate.ai/model?slug=step-3-7-flash · How It Works · Data refreshed daily, snapshot 2026-10-20.