Head to head
Compare models
Pick 2–3 models to overlay their suite radars and line up every stat. Best value in each row is highlighted.
✓ Verified data — every figure is cited. See sources.
Claude Fable 5
Grok 4.5
Claude Opus 4.8
Some models have unverified suites and are omitted from the radar overlay.
| Metric | Claude Fable 5 | Grok 4.5 | Claude Opus 4.8 |
|---|---|---|---|
| Vibe Coding Index | 89.9 ✓ | 87.4 | 85.5 |
| SWE-bench Verified | 95 ✓ | — | 89 |
| Terminal-Bench | 83 ✓ | — | 79 |
| LiveCodeBench | 90 ✓ | 87 | 88 |
| Blended $/M | $20 | $3 ✓ | $10 |
| Input $/M | $10 | $2 ✓ | $5 |
| Output $/M | $50 | $6 ✓ | $25 |
| Output speed (tok/s) | 67 | 91 ✓ | 60 |
| Latency TTFT (s) | 186 | 16.49 ✓ | 23.13 |
| Context | 1M ✓ | 500K | 1M ✓ |
| Released | Jun 2026 | Jul 2026 | May 2026 |
| License | Proprietary | Proprietary | Proprietary |