Model comparison
Claude Fable 5 vs Claude Sonnet 5
Head-to-head evidence from 27 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Fable 5 #2 (Supported); Claude Sonnet 5 #29 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Fable 5 and Claude Sonnet 5 share 27 comparable benchmark results. 3 of 8 categories are comparable. 7 results are unique to Claude Fable 5; 9 to Claude Sonnet 5.
Updated July 23, 2026- Shared results
- 27
- Claude Fable 5 only
- 7
- Claude Sonnet 5 only
- 9
- Comparable categories
- 3 / 8
Pick Claude Fable 5 if you want the stronger benchmark profile. Claude Sonnet 5 only becomes the better choice if multimodal & grounded is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 27 shared benchmark results across 5 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Claude Fable 5 is clearly ahead on the BenchAlign aggregate, 83.68 to 65.32. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Fable 5's sharpest advantage is in coding, where it averages 89.2 against 76.7. The single biggest benchmark swing on the page is SWE-bench Pro, 80% to 63.2%. Claude Sonnet 5 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Claude Fable 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $2.00 input / $10.00 output per 1M tokens for Claude Sonnet 5. That is roughly 5.0x on output cost alone. Claude Fable 5 gives you the larger context window at 1M+, compared with 1M for Claude Sonnet 5.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Fable 5 | Δ | Claude Sonnet 5 |
|---|---|---|---|
| Multimodal | Claude Fable 557.9 | Margin→ 30.4 | Claude Sonnet 588.3 |
| Coding | Claude Fable 589.2 | Margin← 12.5 | Claude Sonnet 576.7 |
| Agentic | Claude Fable 584.6 | Margin← 2.7 | Claude Sonnet 581.9 |
| Knowledge | Claude Fable 5Not measured | MarginNo overlap | Claude Sonnet 557.4 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Pro
CodingA 80%B 63.2%Winner: Claude Fable 5Δ 16.8SWE-bench Pro: Claude Fable 5 scored 80%; Claude Sonnet 5 scored 63.2%. Claude Fable 5 wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 95%B 85.2%Winner: Claude Fable 5Δ 9.8SWE-bench Verified: Claude Fable 5 scored 95%; Claude Sonnet 5 scored 85.2%. Claude Fable 5 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 84.3%B 80.4%Winner: Claude Fable 5Δ 3.9Terminal-Bench 2.0: Claude Fable 5 scored 84.3%; Claude Sonnet 5 scored 80.4%. Claude Fable 5 wins this benchmark. - Source ↗
OSWorld-Verified
AgenticA 85%B 81.2%Winner: Claude Fable 5Δ 3.8OSWorld-Verified: Claude Fable 5 scored 85%; Claude Sonnet 5 scored 81.2%. Claude Fable 5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Fable 5 | Claude Sonnet 5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Fable 5$10 input / $50 output | Claude Sonnet 5$2 input / $10 output | Claude Sonnet 5 has the lower combined listed price. |
| Generation speedtokens per second | Claude Fable 5Not available | Claude Sonnet 5Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Fable 5Not available | Claude Sonnet 5Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Fable 51M+ | Claude Sonnet 51M | Claude Fable 5 lists the larger context window. |
Benchmark Deep Dive
AgenticClaude Fable 5 wins15 benchmarks
| Benchmark | Claude Fable 5 | Claude Sonnet 5 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 84.3% | 80.4% | Claude Fable 5 leads |
| OSWorld-VerifiedSource | 85% | 81.2% | Claude Fable 5 leads |
| GDPval-AASource | 1748 | 1607 | Claude Fable 5 leads |
| AA Agentic IndexSource | 52.8% | 46.7% | Claude Fable 5 leads |
| τ²-bench resultsSource | 98.5% | — | Not comparable |
| GDPval-AASource | 62.4% | 55.4% | Claude Fable 5 leads |
| AA BriefcaseSource | 1574 | 1388 | Claude Fable 5 leads |
| AA AutomationBenchSource | 48.6% | 39.2% | Claude Fable 5 leads |
| AA EnterpriseOps-GymSource | 51.1% | 44.7% | Claude Fable 5 leads |
| AA Harvey LABSource | 93.6% | 90.1% | Claude Fable 5 leads |
| AA Tau3 BankingSource | 26.8% | 28.2% | Claude Sonnet 5 leads |
| terminalBenchHardSource | 62.9% | — | Not comparable |
| aaTerminalBench21Source | 84.6% | 80.5% | Claude Fable 5 leads |
| BrowseCompSource | — | 84.7% | Not comparable |
| HLE w/ toolsSource | — | 57.4% | Not comparable |
CodingClaude Fable 5 wins11 benchmarks
| Benchmark | Claude Fable 5 | Claude Sonnet 5 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 95% | 85.2% | Claude Fable 5 leads |
| SWE-bench ProSource | 80% | 63.2% | Claude Fable 5 leads |
| FrontierCode 1.1 MainSource | 53.5% | 42.7% | Claude Fable 5 leads |
| Terminal-Bench 2.0Source | 84.3% | 80.4% | Claude Fable 5 leads |
| cursorBench31Source | 70.6% | — | Not comparable |
| cursorBench32Source | 70.5% | 61.5% | Claude Fable 5 leads |
| VulcanBench v3Source | 87.0% | — | Not comparable |
| AA Coding IndexSource | 76.5% | 71.5% | Claude Fable 5 leads |
| AA-SciCodeSource | 60.2% | 53.6% | Claude Fable 5 leads |
| SWE MultilingualSource | — | 78.3% | Not comparable |
| SWE MultimodalSource | — | 28.1% | Not comparable |
Reasoning2 benchmarks
Knowledge8 benchmarks
| Benchmark | Claude Fable 5 | Claude Sonnet 5 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 59.9% | 53.4% | Claude Fable 5 leads |
| AA-GPQA DiamondSource | 92.6% | 91.1% | Claude Fable 5 leads |
| AA-HLESource | 53.3% | 39.6% | Claude Fable 5 leads |
| AA-Omniscience IndexSource | 40.2% | 15.3% | Claude Fable 5 leads |
| AA-Omniscience AccuracySource | 61.4% | 38.3% | Claude Fable 5 leads |
| AA-Omniscience Hallucination RateSource | 54.9% | 37.3% | Claude Sonnet 5 leads |
| HLESource | — | 57.4% | Not comparable |
| HLE w/o toolsSource | — | 43.2% | Not comparable |
MultimodalClaude Sonnet 5 wins6 benchmarks
Inst. Following1 benchmarks
| Benchmark | Claude Fable 5 | Claude Sonnet 5 | Result |
|---|---|---|---|
| AA-IFBenchSource | 63.5% | — | Not comparable |
Frequently Asked Questions (4)
Which is better, Claude Fable 5 or Claude Sonnet 5?
Claude Fable 5 is ahead on BenchLM's BenchAlign leaderboard, 83.68 to 65.32. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 80% and 63.2%.
Which is better for coding, Claude Fable 5 or Claude Sonnet 5?
Claude Fable 5 has the edge for coding in this comparison, averaging 89.2 versus 76.7. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Claude Fable 5 or Claude Sonnet 5?
Claude Fable 5 has the edge for agentic tasks in this comparison, averaging 84.6 versus 81.9. Inside this category, AA Briefcase is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Claude Fable 5 or Claude Sonnet 5?
Claude Sonnet 5 has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 57.9. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.