Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Agnes 2.5 Pro Beta | Step 3.5 Flash 2603 |
|---|---|---|
| Input ($/M tokens) | $0.1 | $0.1 |
| Output ($/M tokens) | $0.3 | $0.3 |
Verdict. Agnes 2.5 Pro Beta wins the overall benchmark matchup 2–0 across 2 overlapping categories, but raw benchmark score is only one input to the decision.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, Step 3.5 Flash 2603 is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Step 3.5 Flash 2603 makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Agnes 2.5 Pro Beta is strongest on Coding Index (62.3), Intelligence Index (49.1). Step 3.5 Flash 2603 leads on Intelligence Index (26.5).
Speed. Throughput is comparable — 168 tok/s vs 205 tok/s — so generation speed shouldn't drive your choice here. Look at the per-benchmark wins instead.
Provider. Sapiens AI and StepFun sell to overlapping but distinct developer audiences: Sapiens AI tends to ship frontier reasoning models with premium positioning, while StepFun often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Agnes 2.5 Pro Beta costs $7.50 ($90/year); Step 3.5 Flash 2603 costs $7.50 ($90/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Agnes 2.5 Pro Beta ≈ $1.10/run, Step 3.5 Flash 2603 ≈ $1.10/run. At agent/realtime scale (200M input / 100M output per million requests): Agnes 2.5 Pro Beta ≈ $50/run, Step 3.5 Flash 2603 ≈ $50/run.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Data from Artificial Analysis API — 12 benchmarks
Both models have similar pricing. Check the detailed breakdown above for input vs output token costs.
Agnes 2.5 Pro Beta wins 2 out of 12 benchmarks compared to 0 for Step 3.5 Flash 2603. See the detailed benchmark chart above for per-category results.
Step 3.5 Flash 2603 generates tokens faster at 205 tok/s vs 168 tok/s. However, Step 3.5 Flash 2603 has lower time-to-first-token (1.06s vs 2.00s).
Choose based on your priorities: both are similarly priced, Agnes 2.5 Pro Beta for stronger benchmark performance, and Step 3.5 Flash 2603 for faster generation. For latency-sensitive apps, check the TTFT comparison above.