Model comparison
Grok 4.3 vs Soofi S 30B-A3B
Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use BenchLM's provisional ranking lane.
Evidence parity. Grok 4.3 and Soofi S 30B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 29 results are unique to Grok 4.3; 7 to Soofi S 30B-A3B.
Updated July 15, 2026- Shared results
- 1
- Grok 4.3 only
- 29
- Soofi S 30B-A3B only
- 7
- Comparable categories
- 1 / 8
Pick Grok 4.3 if you want the stronger benchmark profile. Soofi S 30B-A3B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Grok 4.3 is clearly ahead on the provisional aggregate, 63 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Grok 4.3 is also the more expensive model on tokens at $1.25 input / $2.50 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Soofi S 30B-A3B. That is roughly Infinityx on output cost alone. Grok 4.3 is the reasoning model in the pair, while Soofi S 30B-A3B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
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 | Grok 4.3 | Δ | Soofi S 30B-A3B |
|---|---|---|---|
| Knowledge | Grok 4.342.4 | Margin→ 7.5 | Soofi S 30B-A3B49.9 |
| Coding | Grok 4.347.3 | MarginNo overlap | Soofi S 30B-A3BNot measured |
| Multimodal | Grok 4.378.1 | MarginNo overlap | Soofi S 30B-A3BNot measured |
| Inst. Following | Grok 4.381.3 | MarginNo overlap | Soofi S 30B-A3BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
GPQA
KnowledgeA 90.1%B 43.4%Winner: Grok 4.3Δ 46.7GPQA: Grok 4.3 scored 90.1%; Soofi S 30B-A3B scored 43.4%. Grok 4.3 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Grok 4.3 | Soofi S 30B-A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Grok 4.3$1.25 input / $2.5 output | Soofi S 30B-A3B$0 input / $0 output | Soofi S 30B-A3B has the lower combined listed price. |
| Generation speedtokens per second | Grok 4.3209 tok/s | Soofi S 30B-A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Grok 4.312.36 s | Soofi S 30B-A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Grok 4.31M | Soofi S 30B-A3B1M | Listed context windows are equal. |
Benchmark Deep Dive
Agentic11 benchmarks
| Benchmark | Grok 4.3 | Soofi S 30B-A3B | Result |
|---|---|---|---|
| τ²-bench resultsSource | 97.7% | — | Not comparable |
| GDPval-AASource | 29.2% | — | Not comparable |
| AA Agentic IndexSource | 24.1% | — | Not comparable |
| APEX-Agents-AASource | 17.0% | — | Not comparable |
| GDPval-AASource | 1085 | — | Not comparable |
| Gert LabsSource | 43.86% | — | Not comparable |
| ResearchClawBenchSource | 12.4% | — | Not comparable |
| AA BriefcaseSource | 752 | — | Not comparable |
| AA EnterpriseOps-GymSource | 26.3% | — | Not comparable |
| AA Harvey LABSource | 0.0% | — | Not comparable |
| AA ITBenchSource | 32.7% | — | Not comparable |
Coding5 benchmarks
Reasoning4 benchmarks
KnowledgeSoofi S 30B-A3B wins11 benchmarks
| Benchmark | Grok 4.3 | Soofi S 30B-A3B | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 37.6% | — | Not comparable |
| GPQASource | 90.1% | 43.4% | Grok 4.3 leads |
| HLESource | 35% | — | Not comparable |
| AA-Omniscience AccuracySource | 34.6% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 25.0% | — | Not comparable |
| AA-GPQA DiamondSource | 90.1% | — | Not comparable |
| AA-HLESource | 35.0% | — | Not comparable |
| AA-Omniscience IndexSource | 18.3% | — | Not comparable |
| GPQA-DSource | — | 43.4% | Not comparable |
| MMLU-ProSource | — | 51.4% | Not comparable |
| AGIEvalSource | — | 66.9% | Not comparable |
Math1 benchmarks
| Benchmark | Grok 4.3 | Soofi S 30B-A3B | Result |
|---|---|---|---|
| GSM8KSource | — | 86.1% | Not comparable |
Multimodal3 benchmarks
Frequently Asked Questions (2)
Which is better, Grok 4.3 or Soofi S 30B-A3B?
Grok 4.3 is ahead on BenchLM's provisional leaderboard, 63 to 45. The biggest single separator in this matchup is GPQA, where the scores are 90.1% and 43.4%.
Which is better for knowledge tasks, Grok 4.3 or Soofi S 30B-A3B?
Soofi S 30B-A3B has the edge for knowledge tasks in this comparison, averaging 49.9 versus 42.4. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.