Reasoning
Like-for-like- Claude Fable 5.1
- 90.0
- Grok 4.20
- 53.3
- Weighted basis
- 1 vs 1 rows
- Reading
- Claude Fable 5.1 leads
Claude Fable 5.1 vs Grok 4.20
Updated September 1, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Fable 5.1 has the higher public score estimate, 82.74 versus 55.42, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
3 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
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.
Long documents
Prompts that approach the documented context limit
Grok 4.20
Grok 4.20 has the larger documented context window.
Confidence: documented
Chat turn cost
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.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Grok 4.20
Grok 4.20 has the lower estimated token cost for this stated workload. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
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.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
15 Claude Fable 5.1 only
3 Shared
15 Grok 4.20 only
- Shared results
- 3
- Claude Fable 5.1 only
- 15
- Grok 4.20 only
- 15
- Like-for-like categories
- 1 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Directional only- Claude Fable 5.1
- 81.2
- Grok 4.20
- 67.1
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Agentic
Not comparable- Claude Fable 5.1
- Not measured
- Grok 4.20
- 47.1
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Fable 5.1
- 65.0
- Grok 4.20
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Claude Fable 5.1
- Not measured
- Grok 4.20
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Fable 5.1
- Not measured
- Grok 4.20
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Fable 5.1
- Not measured
- Grok 4.20
- 70.1
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Fable 5.1
- Not measured
- Grok 4.20
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Fable 5.1 | Grok 4.20 | Weighted basis | Reading |
|---|---|---|---|---|
| Reasoning | 90.0 | 53.3 | Like-for-like1 vs 1 rows | Claude Fable 5.1 leads |
| Coding | 81.2 | 67.1 | Directional only1 vs 2 rows | Directional only |
| Agentic | Not measured | 47.1 | Not comparable0 vs 1 rows | Not comparable |
| Knowledge | 65.0 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 70.1 | Not comparable0 vs 2 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
Shape of the matched evidence
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.
ARC-AGI-2
Reasoning
SWE-bench Pro
Coding
What each workload costs
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.
Chat turn
1K fresh input + 500 output tokens
- Claude Fable 5.1
- $0.035
- Fits in one request
- Grok 4.20
- $0.005
- Fits in one request
Grok 4.20 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Fable 5.1
- $0.65
- Fits in one request
- Grok 4.20
- $0.118
- Fits in one request
Grok 4.20 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Fable 5.1
- $0.75
- Fits in one request
- Grok 4.20
- $0.5
- Fits in one request
- Cached input priced at the published list-input rate
Grok 4.20 has the lower modeled cost
Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Fable 5.1Grok 4.20
Context window
Maximum documented context; output-token limits may be lower.
Claude Fable 5.1
Grok 4.20
2M
API model ID
Claude Fable 5.1
claude-fable-5-1
Anthropic Fable 5.1 and Mythos 5.1 launchGrok 4.20
Not sourced
Cached-input rate
A 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 launchGrok 4.20
Not published
Documented inputs
Claude Fable 5.1
Not sourced
Grok 4.20
Not sourced
Documented outputs
Claude Fable 5.1
Not sourced
Grok 4.20
Not sourced
Provider availability
Claude Fable 5.1
Generally Available · Claude API, Claude products, AWS, Google Cloud, Microsoft Azure
Anthropic Fable 5.1 and Mythos 5.1 launchGrok 4.20
Not sourced
Reasoning profile
Claude Fable 5.1
Reasoning
Grok 4.20
Reasoning
Weight access
Claude Fable 5.1
Proprietary
Grok 4.20
Proprietary
License
Claude Fable 5.1
Proprietary
Grok 4.20
Proprietary
Release date
Claude Fable 5.1
2026-09-01
Grok 4.20
2026-03-10
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Claude Fable 5.1 has the higher public score estimate, 82.74 versus 55.42, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.65 vs $0.118. Cache-heavy agent loop: $0.75 vs $0.5.
- Context tradeoff
- Grok 4.20 has the larger documented window (2M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence33 rows
Agentic
Terminal-Bench 4.0
Claude Fable 5.155.80%SourceGrok 4.20—Not directly comparable
Terminal-Bench-Science 0.1
Claude Fable 5.152.6%SourceGrok 4.20—Not directly comparable
OSWorld 2.0
Claude Fable 5.141.7%SourceGrok 4.20—Not directly comparable
AutomationBench
Claude Fable 5.131.4%SourceGrok 4.20—Not directly comparable
Toolathlon-Verified
Claude Fable 5.177.8%SourceGrok 4.20—Not directly comparable
Toolathlon Verified Pass@3
Claude Fable 5.181.5%SourceGrok 4.20—Not directly comparable
Toolathlon Verified Pass³
Claude Fable 5.173.1%SourceGrok 4.20—Not directly comparable
Toolathlon Verified avg. turns
Claude Fable 5.123.7 turnsSourceGrok 4.20—Not directly comparable
Terminal-Bench 2.0
Claude Fable 5.1—Grok 4.2047.1%SourceNot directly comparable
DeepSearchQA
Claude Fable 5.1—Grok 4.2062.8%SourceNot directly comparable
Gert Labs
Claude Fable 5.1—Grok 4.2038.36%SourceNot directly comparable
Coding
SWE-bench Pro
Claude Fable 5.181.2%SourceGrok 4.2051.8%SourceClaude Fable 5.1 leads this result
SWE Multilingual
Claude Fable 5.189.1%SourceGrok 4.20—Not directly comparable
SWE Multimodal
Claude Fable 5.154.7%SourceGrok 4.20—Not directly comparable
deepSwe
Claude Fable 5.167.4%SourceGrok 4.20—Not directly comparable
ProgramBench
Claude Fable 5.187.6%SourceGrok 4.20—Not directly comparable
cursorBench32
Claude Fable 5.173.4%SourceGrok 4.20—Not directly comparable
LiveCodeBench Pro
Claude Fable 5.1—Grok 4.2074.2%SourceNot directly comparable
SWE-bench Verified
Claude Fable 5.1—Grok 4.2076.7%SourceNot directly comparable
Vibe Code Bench
Claude Fable 5.1—Grok 4.204.06%SourceNot directly comparable
Reasoning
Knowledge
HLE
Claude Fable 5.165%SourceGrok 4.20—Not directly comparable
HLE w/o tools
Claude Fable 5.160.9%SourceGrok 4.2031.6%SourceClaude Fable 5.1 leads this result
GPQA-D
Claude Fable 5.1—Grok 4.2088.5%SourceNot directly comparable
HealthBench Hard
Claude Fable 5.1—Grok 4.2020.3%SourceNot directly comparable
MedXpertQA (Text)
Claude Fable 5.1—Grok 4.2050.2%SourceNot directly comparable
Multimodal
MMMU-Pro
Claude Fable 5.1—Grok 4.2075.2%SourceNot directly comparable
CharXiv
Claude Fable 5.1—Grok 4.2060.9%SourceNot directly comparable
ERQA
Claude Fable 5.1—Grok 4.2054.1%SourceNot directly comparable
SimpleVQA
Claude Fable 5.1—Grok 4.2057.4%SourceNot directly comparable
MedXpertQA (MM)
Claude Fable 5.1—Grok 4.2065.8%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Fable 5.1 or Grok 4.20?
Claude Fable 5.1 has the higher public score estimate, 82.74 versus 55.42, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Fable 5.1 or Grok 4.20?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Claude Fable 5.1 or Grok 4.20?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Claude Fable 5.1 or Grok 4.20?
For the stated presets, chat costs $0.035 on Claude Fable 5.1 and $0.005 on Grok 4.20; repository review costs $0.65 and $0.118; the cache-heavy agent loop costs $0.75 and $0.5. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Fable 5.1 or Grok 4.20?
Grok 4.20 has the larger documented context window: 2M, compared with 1M.
Related comparisons
Last updated September 1, 2026
Watch Claude Fable 5.1 vs Grok 4.20
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.