Claude 4.5 Haiku (Reasoning) vs Step 5 Preview
Which is better for the money: Claude 4.5 Haiku (Reasoning) by Anthropic or Step 5 Preview by StepFun? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Step 5 Preview scores 26.8 points higher (43.7 vs 16.9) but costs 2.0× as much to run the benchmark ($1190 vs $594; both premium class). Pick Step 5 Preview when the extra intelligence is worth the premium, otherwise Claude 4.5 Haiku (Reasoning).
| Metric | Claude 4.5 Haiku (Reasoning) | Step 5 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 16.9 | 43.7 | +158.6% Step 5 Preview is 2.6× more intelligent |
| Total AA cost (lower is better) | $594.08 | $1,190.26 | +100.4% Step 5 Preview is 2.0× more expensive |
| End-to-end time (lower is better) | 23.18s | 12.06s | −48.0% Step 5 Preview is 48.0% faster |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $1.00 / $2.70 | |
| Input modalities | Text, Image | Text, Image |
Step 5 Preview vs Claude 4.5 Haiku (Reasoning): 158.6% more intelligence, 100.4% more cost to run the AA benchmark, and 48.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude 4.5 Haiku (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
- Step 5 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Claude 4.5 Haiku (Reasoning)Step 5 PreviewToday's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-4-5-haiku-reasoning/step-5 · Markdown: /api/v1/compare/claude-4-5-haiku-reasoning/step-5?format=md · llms.txt · agent skill