Agentic
Not comparable- Grok 4.20
- 47.1
- Soofi S 30B-A3B
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Grok 4.20 vs Soofi S 30B-A3B
Updated August 29, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
1 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
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
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
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
17 Grok 4.20 only
1 Shared
7 Soofi S 30B-A3B only
- Shared results
- 1
- Grok 4.20 only
- 17
- Soofi S 30B-A3B only
- 7
- Like-for-like categories
- 0 / 8
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
Not comparable- Grok 4.20
- 67.1
- Soofi S 30B-A3B
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Grok 4.20
- 53.3
- Soofi S 30B-A3B
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Grok 4.20
- Not measured
- Soofi S 30B-A3B
- 49.9
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Math
Not comparable- Grok 4.20
- Not measured
- Soofi S 30B-A3B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Grok 4.20
- Not measured
- Soofi S 30B-A3B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Grok 4.20
- 70.1
- Soofi S 30B-A3B
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Grok 4.20
- Not measured
- Soofi S 30B-A3B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Grok 4.20 | Soofi S 30B-A3B | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 47.1 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Coding | 67.1 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Reasoning | 53.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Knowledge | Not measured | 49.9 | Not comparable0 vs 2 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 | 70.1 | Not measured | Not comparable2 vs 0 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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
- Grok 4.20
- $0.005
- Fits in one request
- Soofi S 30B-A3B
- Self-hosted; infrastructure cost varies
- Fits in one request
Soofi S 30B-A3B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Grok 4.20
- $0.118
- Fits in one request
- Soofi S 30B-A3B
- Self-hosted; infrastructure cost varies
- Fits in one request
Soofi S 30B-A3B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Grok 4.20
- $0.5
- Fits in one request
- Cached input priced at the published list-input rate
- Soofi S 30B-A3B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate. Soofi S 30B-A3B has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGrok 4.20Soofi S 30B-A3B
Context window
Maximum documented context; output-token limits may be lower.
Grok 4.20
2M
Soofi S 30B-A3B
1M
API model ID
Grok 4.20
Not sourced
Soofi S 30B-A3B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Grok 4.20
Not published
Soofi S 30B-A3B
No comparable hosted API rate
Documented inputs
Grok 4.20
Not sourced
Soofi S 30B-A3B
Not sourced
Documented outputs
Grok 4.20
Not sourced
Soofi S 30B-A3B
Not sourced
Provider availability
Grok 4.20
Not sourced
Soofi S 30B-A3B
Not sourced
Reasoning profile
Grok 4.20
Reasoning
Soofi S 30B-A3B
Non-Reasoning
Weight access
Grok 4.20
Proprietary
Soofi S 30B-A3B
Open Weight
License
Grok 4.20
Proprietary
Soofi S 30B-A3B
Open Weight
Release date
Grok 4.20
2026-03-10
Soofi S 30B-A3B
2026-07-10
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
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- 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 evidence25 rows
Agentic
Coding
LiveCodeBench Pro
Grok 4.2074.2%SourceSoofi S 30B-A3B—Not directly comparable
SWE-bench Verified
Grok 4.2076.7%SourceSoofi S 30B-A3B—Not directly comparable
SWE-bench Pro
Grok 4.2051.8%SourceSoofi S 30B-A3B—Not directly comparable
Vibe Code Bench
Grok 4.204.06%SourceSoofi S 30B-A3B—Not directly comparable
HumanEval
Grok 4.20—Soofi S 30B-A3B73.8%SourceNot directly comparable
Reasoning
Knowledge
GPQA-D
Grok 4.2088.5%SourceSoofi S 30B-A3B43.4%SourceGrok 4.20 leads this result
HLE w/o tools
Grok 4.2031.6%SourceSoofi S 30B-A3B—Not directly comparable
HealthBench Hard
Grok 4.2020.3%SourceSoofi S 30B-A3B—Not directly comparable
MedXpertQA (Text)
Grok 4.2050.2%SourceSoofi S 30B-A3B—Not directly comparable
GPQA
Grok 4.20—Soofi S 30B-A3B43.4%SourceNot directly comparable
MMLU-Pro
Grok 4.20—Soofi S 30B-A3B51.4%SourceNot directly comparable
AGIEval
Grok 4.20—Soofi S 30B-A3B66.9%SourceNot directly comparable
Math
GSM8K
Grok 4.20—Soofi S 30B-A3B86.1%SourceNot directly comparable
Multimodal
MMMU-Pro
Grok 4.2075.2%SourceSoofi S 30B-A3B—Not directly comparable
CharXiv
Grok 4.2060.9%SourceSoofi S 30B-A3B—Not directly comparable
ERQA
Grok 4.2054.1%SourceSoofi S 30B-A3B—Not directly comparable
SimpleVQA
Grok 4.2057.4%SourceSoofi S 30B-A3B—Not directly comparable
MedXpertQA (MM)
Grok 4.2065.8%SourceSoofi S 30B-A3B—Not directly comparable
Frequently asked questions
Which is better, Grok 4.20 or Soofi S 30B-A3B?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Grok 4.20 or Soofi S 30B-A3B?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, Grok 4.20 or Soofi S 30B-A3B?
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, Grok 4.20 or Soofi S 30B-A3B?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Grok 4.20 or Soofi S 30B-A3B?
Grok 4.20 has the larger documented context window: 2M, compared with 1M.
Related comparisons
Last updated August 29, 2026
Watch Grok 4.20 vs Soofi S 30B-A3B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.