Claude Fable 5 vs Step 3.7 Flash: Benchmarks, Pricing & Capabilities Compared
TL;DR — Claude Fable 5 wins for reasoning + long-context · Step 3.7 Flash wins for cost.
Claude Fable 5 Anthropic
- Released
- 2026-06-09
- Context window
- 1M tokens
- Input price
- $10.00 / Mtok
- Output price
- $50.00 / Mtok
Step 3.7 Flash StepFun
- Released
- 2026-05-29
- Context window
- 256K tokens
- Input price
- $0.20 / Mtok
- Output price
- $1.15 / Mtok
Benchmark comparison
| Benchmark | Claude Fable 5 | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 92.6% ✓ | 80.9% |
| HLE | 53.3% ✓ | 19.9% |
| IF-Bench | 63.5% | 67.3% ✓ |
| LiveCodeBench Reasoning | 70.0% ✓ | 63.7% |
| SciCode | 60.2% ✓ | 40.0% |
| TAU2-bench | 98.5% | 98.5% |
| TerminalBench-Hard | 62.9% ✓ | 35.6% |
Pricing comparison
| Metric | Claude Fable 5 | Step 3.7 Flash |
|---|---|---|
| Input ($/Mtok) | $10.00 | $0.20 |
| Output ($/Mtok) | $50.00 | $1.15 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $60.00 | $1.35 |
Context window & modalities
| Attribute | Claude Fable 5 | Step 3.7 Flash |
|---|---|---|
| Context window | 1M tokens | 256K tokens |
| Input modalities | text, image | text, image |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ Claude Fable 5
Basis: GPQA Diamond
Claude Fable 5 92.6% vs Step 3.7 Flash 80.9% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ Claude Fable 5
Basis: Context window
Claude Fable 5 1M tokens vs Step 3.7 Flash 256K tokens.
Cost
→ Step 3.7 Flash
Basis: Input $/Mtok
Claude Fable 5 $10/Mtok vs Step 3.7 Flash $0.2/Mtok input.
Changelog & releases
Claude Fable 5
Released 2026-06-09
Step 3.7 Flash
Released 2026-05-29