Compare
Claude Fable 5.1 vs GPT-6 Astra
Side by side: capability scores, runtime measurements and every published price component. A value no source returned stays explicitly unavailable.
Comparison set
Check two to four models below, then press Compare — the URL and evidence below only update once you do.
Decision evidence
Exact source values, missing states, and pair-derived deltas stay separate.
Capability shape
Exact capability values
Evidence key: ObservedUnavailable
| Capability | Claude Fable 5.1 | GPT-6 Astra |
|---|---|---|
| Agentic | 60.8 | 87.1 |
| Coding | 90.4 | 75.2 |
| Knowledge | 97.5 | 86.4 |
| Reasoning | 79.4 | 89.5 |
| Multimodal & Grounded | Unavailable | 82.9 |
| Instruction Following | Unavailable | Unavailable |
| Math | Unavailable | 85 |
| Overall | 84.58 | 83.79 |
Runtime
Time to first token and throughput, exactly as the runtime source published them.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Economics
Source rates plus a labelled 75% input / 25% output blended cost.
Runtime and price matrix
| Metric | Claude Fable 5.1 | GPT-6 Astra |
|---|---|---|
| Input / 1M | $10.00 | $10.00 |
| Output / 1M | $50.00 | $50.00 |
| Cache read / 1M | $0.25 | $1.00 |
| Cache write / 1M | Unavailable | $12.50 |
| Blended / 1M (75% input / 25% output) | $20.00 | $20.00 |
| Cost per successful task (LiveBench) | Unavailable | Unavailable |
| Time to first token | 279.9 s | 253.04 s |
| Throughput | 69 tok/s | 69 tok/s |
| Context window | 1M tokens | 1.05M tokens |
| Release date | 2026-09-01 | 2026-09-03 |
| Access | Proprietary | Proprietary |
Decision deltas
Each row comes from the pair comparison source. A null basis or average stays unavailable rather than being inferred from the capability table.
Claude Fable 5.1 versus GPT-6 Astra
benchlm:comparisons · bench-align-v5 · fetched 2026-09-22 · overall delta 0.79 · overall winner A
| Capability | A average | B average | Delta | Winner | Pair basis |
|---|---|---|---|---|---|
| Agentic | 80.2 | 70.6 | 9.60 | A | Supported · #1/154 · Supported · #5/154 · like-for-like · 14 benchmarks |
| Coding | 84.6 | 77 | 7.60 | A | Supported · #1/156 · Supported · #3/156 · like-for-like · 12 benchmarks |
| Knowledge | 87 | 82.9 | 4.10 | A | Supported · #1/186 · Supported · #3/186 · like-for-like · 8 benchmarks |
| Reasoning | 79.4 | 89.5 | -10.10 | Unavailable | #2/19 · #1/19 · directional · 6 benchmarks |
| Multimodal & Grounded | Unavailable | 82.9 | Unavailable | Unavailable | Unranked · 3 rankable rows · not-comparable · 2 benchmarks |
| Instruction Following | Unavailable | Unavailable | Unavailable | Unavailable | not-comparable · 0 benchmarks |
| Math | Unavailable | 85 | Unavailable | Unavailable | Unranked · 1 rankable row · not-comparable · 1 benchmarks |