Claude Fable 5 (Thinking) vs Claude Opus 4.6 (Thinking) vs Spark 1.2
Side-by-side benchmark scores, pricing, and specifications
Specifications
| Specification | | | |
|---|---|---|---|
| Provider | Anthropic | Anthropic | Meta |
| Variant | Thinking | 4.6 Thinking | Spark 1.2 |
| Input price | $10.00/1M | $5.00/1M | — |
| Output price | $50.00/1M | $25.00/1M | — |
| Context window | 1.0M | 1.0M | — |
| Benchmark | Comparison | Claude Fable 5 (Thinking) | Claude Opus 4.6 (Thinking) | Spark 1.2 |
|---|---|---|---|---|
CompositeQuality Score | 112.6%#3 | 97.2%#16 | 104.0%#7 | |
Human preferenceArena ELO | 1,507#1 | 1,505#2 | 1,499#4 | |
General reasoningLiveBench | 83.0%#1 | 74.5%#32 | 78.0%#9 | |
Scientific knowledgeGPQA Diamond | — | 91.3%#11 | — | |
Academic reasoningHLE | — | 40.0%#9 | — | |
Commonsense reasoningSimpleBench | 81.9%#1 | 67.6%#11 | 74.5%#7 | |
MathematicsAIME 2025 | — | 95.6%#2 | — | |
Graduate scienceGSO | — | 41.2%#3 | — | |
Agentic codingSWE-Bench Verified | — | 80.8%#5 | — | |
Agentic tool useTau-Bench | — | 91.9%#1 | — | |
Agentic terminalTerminal-Bench | — | 65.4%#5 | — | |
Visual reasoningARC-AGI-2 | 88.3%#2 | 68.8%#12 | — |
Scores represent the best available variant for each model. Higher is better unless otherwise noted. Bars show relative performance within each benchmark.