Updated November 13, 2026. Rank says Claude Sonnet 5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Claude Sonnet 5 has the higher public point estimate, 63.83 versus 55.29. Their conditional score ranges overlap. These ranges do not establish rank confidence. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Claude Sonnet 5: $2 input / $10 output
Grok 4.20: $1.25 input / $2.50 output
Claude Sonnet 5: 1M
Grok 4.20: 1M
Claude Sonnet 5: June 30, 2026
Grok 4.20: March 10, 2026
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 Sonnet 5
Claude Sonnet 5 has the higher public coding point estimate, 51.7 to 24.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
Claude Sonnet 5
Claude Sonnet 5 has the higher public agentic point estimate, 62.5 to 25.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
1K fresh input + 500 output tokens
Grok 4.20
Grok 4.20 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
Grok 4.20
Grok 4.20 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Grok 4.20
Grok 4.20 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 Sonnet 5 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.
The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
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.
CharXivMultimodal
Normalized gap 27.4HLE w/o toolsKnowledge
Normalized gap 11.6SWE-bench ProCoding
Normalized gap 11.4SWE-bench VerifiedCoding
Normalized gap 8.5LiveCodeBench (Vals)Coding
Normalized gap 1.9Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, 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 Sonnet 5 | Grok 4.20 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 62.5Supported · #22/135 | 25.6Supported · #112/135 | Like-for-likeBenchAlign v5.8 lane · 10 vs 5 public rows | Claude Sonnet 5 leads |
| Coding | 51.7Supported · #40/162 | 24.4Supported · #123/162 | Like-for-likeBenchAlign v5.8 lane · 11 vs 6 public rows | Claude Sonnet 5 leads |
| Knowledge | 61.8Supported · #43/180 | 55.0Supported · #60/180 | Like-for-likeBenchAlign v5.8 lane · 6 vs 6 public rows | Claude Sonnet 5 leads · intervals overlap |
| Multimodal | 60.4Supported · #34/67 | 56.9Estimated · #44/67 | Directional onlyBenchAlign v5.8 lane · 3 vs 5 public rows | Directional only |
| Reasoning | 59.8Estimated · #32/160 | Not ranked | Not comparableBenchAlign v5.8 lane · 0 vs 2 public 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 | 64.9Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, 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
Grok 4.20 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Grok 4.20 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Grok 4.20 has the lower modeled cost
Costs use the listed standard API rates.
Enter a month of tokens to price it at both models’ listed API rates.
Standard listed rates, no batch or volume discounts.
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 Sonnet 5
Grok 4.20
1M
Claude Sonnet 5
claude-sonnet-5
Anthropic model overviewGrok 4.20
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Sonnet 5
$0.2 per 1M cached input tokens
Claude API pricingGrok 4.20
$0.2 per 1M cached input tokens
Claude Sonnet 5
text, image
Anthropic model overviewGrok 4.20
text, image
xAI model page for grok-4.20Claude Sonnet 5
Grok 4.20
Claude Sonnet 5
Generally Available · Claude API
Anthropic model overviewGrok 4.20
Not sourced
Claude Sonnet 5
Reasoning
Grok 4.20
Reasoning
Claude Sonnet 5
Proprietary
Grok 4.20
Proprietary
Claude Sonnet 5
Proprietary
Grok 4.20
Proprietary
Claude Sonnet 5
2026-06-30
Grok 4.20
2026-03-10
Claude Sonnet 5 has the higher public point estimate, 63.83 versus 55.29. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Claude Sonnet 5 has the higher public coding point estimate, 51.7 to 24.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Claude Sonnet 5 has the higher public agentic tasks point estimate, 62.5 to 25.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.007 on Claude Sonnet 5 and $0.0025 on Grok 4.20; repository review costs $0.13 and $0.07; the cache-heavy agent loop costs $0.18 and $0.09. 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 4.1
Not directly comparable
Terminal-Bench 3.0
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
BrowseComp
Not directly comparable
HLE w/ tools
Not directly comparable
OSWorld-Verified
Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Sonnet 5 leads this result
ApprenticeBench
Not directly comparable
MazeBench
Tie
OSWorld 2.1
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
DeepSearchQA
Not directly comparable
Gert Labs
Not directly comparable
SWE-bench Verified
Claude Sonnet 5 leads this result
SWE-bench Pro
Claude Sonnet 5 leads this result
SWE Multilingual
Not directly comparable
SWE Multimodal
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
FrontierCode 1.1 Main
Not directly comparable
CursorBench 3.2
Not directly comparable
VulcanBench CII v1
Not directly comparable
LiveCodeBench (Vals)
Grok 4.20 leads this result
SWE-bench (Vals)
Claude Sonnet 5 leads this result
CursorBench 4.0
Not directly comparable
LiveCodeBench Pro
Not directly comparable
Vibe Code Bench
Not directly comparable
ParseBench
Not directly comparable
CharXiv
Claude Sonnet 5 leads this result
CharXiv w/o tools
Not directly comparable
MMMU-Pro
Not directly comparable
ERQA
Not directly comparable
SimpleVQA
Not directly comparable
MedXpertQA (MM)
Not directly comparable
HLE
Not directly comparable
HLE w/o tools
Claude Sonnet 5 leads this result
HLE-Verified
Not directly comparable
LABBench2
Not directly comparable
GPQA Diamond (Vals)
Claude Sonnet 5 leads this result
MMLU-Pro (Vals)
Claude Sonnet 5 leads this result
GPQA-D
Not directly comparable
HealthBench Hard
Not directly comparable
MedXpertQA (Text)
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 7,000+ subscribers.
Last updated November 13, 2026
