Updated October 17, 2026. Rank says Claude Fable 5.1 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Claude Fable 5.1 has the higher public score estimate, 83.18 versus 79.63, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 29 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Code generation, repair, and software-engineering tasks
Claude Fable 5.1
Claude Fable 5.1 has the higher public coding point estimate, 76.8 to 70.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
Claude Fable 5.1
Claude Fable 5.1 has the higher public agentic point estimate, 80.9 to 78.5, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
1K fresh input + 500 output tokens
Claude Opus 5
Claude Opus 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Claude Opus 5
Claude Opus 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Claude Opus 5
Claude Opus 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Like-for-like · BenchAlign v5.8
Claude Fable 5.1 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
OSWorld 2.0Agentic
Normalized gap 28.9FrontierMath v2 (Tier 4)Math
Normalized gap 14.6AutomationBenchAgentic
Normalized gap 5.4HLE w/o toolsKnowledge
Normalized gap 4.6FrontierMath v2 (Tiers 1-3)Math
Normalized gap 4.6Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | Claude Fable 5.1 | Claude Opus 5 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 80.9Supported · #2/128 | 78.5Supported · #3/128 | Like-for-likeBenchAlign v5.8 lane · 12 vs 21 public rows | Claude Fable 5.1 leads · intervals overlap |
| Coding | 76.8Supported · #3/150 | 70.7Supported · #9/150 | Like-for-likeBenchAlign v5.8 lane · 11 vs 18 public rows | Claude Fable 5.1 leads · intervals overlap |
| Knowledge | 86.9Supported · #2/184 | 82.0Supported · #7/184 | Like-for-likeBenchAlign v5.8 lane · 4 vs 19 public rows | Claude Fable 5.1 leads · intervals overlap |
| Reasoning | 85.2#4/28 | 81.0#11/28 | Directional onlyProvisional lane · 1 vs 2 weighted rows | Directional only |
| Multimodal | Not ranked | 92.2#2/54 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 96.8Unranked · 2 rankable rows | 91.6Unranked · 7 rankable rows | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
1K fresh input + 500 output tokens
Claude Opus 5 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Claude Opus 5 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Claude Opus 5 has the lower modeled cost
Costs use the listed standard API rates.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Claude Fable 5.1
Claude Opus 5
Claude Fable 5.1
claude-fable-5-1
Anthropic Fable 5.1 and Mythos 5.1 launchClaude Opus 5
claude-opus-5
Anthropic model overviewA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Fable 5.1
$0.25 per 1M cached input tokens
Anthropic Fable 5.1 launchClaude Opus 5
$0.5 per 1M cached input tokens
Claude API pricingClaude Fable 5.1
Not sourced
Claude Opus 5
text, image
Anthropic model overviewClaude Fable 5.1
Not sourced
Claude Opus 5
Claude Fable 5.1
Generally Available · Claude API, Claude products, AWS, Google Cloud, Microsoft Azure
Anthropic Fable 5.1 and Mythos 5.1 launchClaude Opus 5
Generally Available · Claude API
Anthropic model overviewClaude Fable 5.1
Reasoning
Claude Opus 5
Reasoning
Claude Fable 5.1
Proprietary
Claude Opus 5
Proprietary
Claude Fable 5.1
Proprietary
Claude Opus 5
Proprietary
Claude Fable 5.1
2026-09-01
Claude Opus 5
2026-07-24
Claude Fable 5.1 has the higher public score estimate, 83.18 versus 79.63, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Claude Fable 5.1 has the higher public coding point estimate, 76.8 to 70.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Claude Fable 5.1 has the higher public agentic tasks point estimate, 80.9 to 78.5, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.035 on Claude Fable 5.1 and $0.0175 on Claude Opus 5; repository review costs $0.65 and $0.325; the cache-heavy agent loop costs $0.75 and $0.45. Costs use the listed standard API rates.
Both models list the same context window, 1M.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 4.0
Not directly comparable
Terminal-Bench-Science 0.1
Not directly comparable
OSWorld 2.0
Claude Opus 5 leads this result
AutomationBench
Claude Fable 5.1 leads this result
Toolathlon-Verified
Claude Opus 5 leads this result
Toolathlon Verified Pass@3
Claude Opus 5 leads this result
Toolathlon Verified Pass³
Tie
Toolathlon Verified avg. turns
Claude Fable 5.1 leads this result
Terminal-Bench 2.1 (Vals)
Claude Fable 5.1 leads this result
ApprenticeBench
Shared sourceClaude Fable 5.1 leads this result
CWE-bench v1
Not directly comparable
MazeBench
Claude Opus 5 leads this result
Terminal-Bench 3.0
Not directly comparable
BrowseComp
Not directly comparable
HLE w/ tools
Not directly comparable
DeepSearchQA
Not directly comparable
DRACO
Not directly comparable
BrowseComp (10-agent, prerelease)
Not directly comparable
MCP Atlas
Not directly comparable
MCP-Atlas claim coverage
Not directly comparable
LAB all-pass (Anthropic harness)
Not directly comparable
LAB criterion-pass (Anthropic harness)
Not directly comparable
LAB all-pass (Harvey held-out)
Not directly comparable
LAB criterion-pass (Harvey held-out)
Not directly comparable
Bug Hunt Bench
Shared sourceClaude Fable 5.1 leads this result
SWE-bench Pro
Claude Fable 5.1 leads this result
SWE Multilingual
Claude Opus 5 leads this result
SWE Multimodal
Claude Opus 5 leads this result
DeepSWE
Claude Opus 5 leads this result
FrontierSWE v2
Shared sourceClaude Fable 5.1 leads this result
ProgramBench
Claude Opus 5 leads this result
CursorBench 3.2
Shared sourceClaude Fable 5.1 leads this result
LiveCodeBench (Vals)
Claude Fable 5.1 leads this result
CursorBench 4.0
Shared sourceClaude Fable 5.1 leads this result
PostTrainBench v1.1
Claude Fable 5.1 leads this result
SWE-bench Verified
Not directly comparable
FrontierCode 1.1 Main
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
ProgramBench (episode 1)
Not directly comparable
VulcanBench v3
Not directly comparable
VulcanBench CII v1
Not directly comparable
SWE-bench (Vals)
Not directly comparable
ARC-AGI-1
Tie
ARC-AGI-2
Claude Opus 5 leads this result
GraphWalks BFS 256K–1M
Not directly comparable
ARC-AGI-3
Not directly comparable
Chartography (no tools)
Not directly comparable
Chartography (tools)
Not directly comparable
BenchCAD Vision2Code (no tools)
Not directly comparable
BenchCAD Vision2Code (tools)
Not directly comparable
GDP.pdf (no tools)
Not directly comparable
GDP.pdf (tools)
Not directly comparable
OfficeQA
Not directly comparable
OfficeQA Pro
Not directly comparable
HLE
Claude Fable 5.1 leads this result
HLE w/o tools
Claude Fable 5.1 leads this result
GPQA Diamond (Vals)
Tie
MMLU-Pro (Vals)
Claude Fable 5.1 leads this result
HLE-Verified
Not directly comparable
LABBench2
Not directly comparable
HealthBench (raw)
Not directly comparable
HealthBench (length-adjusted)
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Professional (raw)
Not directly comparable
BioMysteryBench (human-solvable)
Not directly comparable
BioMysteryBench (human-difficult)
Not directly comparable
SpatialBench Verified
Not directly comparable
SingleCellBench
Not directly comparable
ProteinGym Hard
Not directly comparable
Protein Design
Not directly comparable
Organic chemistry V2
Not directly comparable
Protocols (troubleshooting)
Not directly comparable
Protocols (understanding)
Not directly comparable
Gray Swan IPI (15 attempts)
Shared sourceClaude Fable 5.1 leads this result
FrontierMath v2 (Tiers 1-3)
Shared sourceClaude Fable 5.1 leads this result
FrontierMath v2 (Tier 4)
Shared sourceClaude Fable 5.1 leads this result
IMO 2026
Not directly comparable
RiemannBench (no tools)
Not directly comparable
RiemannBench (tools)
Not directly comparable
ArXivMath Jun. 2026 (no tools)
Not directly comparable
ArXivMath Jun. 2026 (tools)
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 17, 2026
