Model comparison
DeepSeek V4 Flash Base vs Soofi S 30B-A3B
Head-to-head evidence from 6 shared benchmark results across 4 categories. Overall scores shown here use BenchLM's provisional ranking lane.
Evidence parity. DeepSeek V4 Flash Base and Soofi S 30B-A3B share 6 comparable benchmark results. 1 of 8 categories are comparable. 18 results are unique to DeepSeek V4 Flash Base; 2 to Soofi S 30B-A3B.
Updated July 15, 2026- Shared results
- 6
- DeepSeek V4 Flash Base only
- 18
- Soofi S 30B-A3B only
- 2
- Comparable categories
- 1 / 8
Pick Soofi S 30B-A3B if you want the stronger benchmark profile. DeepSeek V4 Flash Base only becomes the better choice if knowledge is the priority.
Confidence note. This is a partial-evidence comparison with 6 shared benchmark results across 4 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Soofi S 30B-A3B is clearly ahead on the provisional aggregate, 45 to 40. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
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 | DeepSeek V4 Flash Base | Δ | Soofi S 30B-A3B |
|---|---|---|---|
| Knowledge | DeepSeek V4 Flash Base56.5 | Margin← 6.6 | Soofi S 30B-A3B49.9 |
| Reasoning | DeepSeek V4 Flash Base44.7 | MarginNo overlap | Soofi S 30B-A3BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
MMLU-Pro
KnowledgeA 68.3%B 51.4%Winner: DeepSeek V4 Flash BaseΔ 16.9MMLU-Pro: DeepSeek V4 Flash Base scored 68.3%; Soofi S 30B-A3B scored 51.4%. DeepSeek V4 Flash Base wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | DeepSeek V4 Flash Base | Soofi S 30B-A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | DeepSeek V4 Flash BaseNot available | Soofi S 30B-A3B$0 input / $0 output | A complete price comparison is not available. |
| Generation speedtokens per second | DeepSeek V4 Flash BaseNot available | Soofi S 30B-A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | DeepSeek V4 Flash BaseNot available | Soofi S 30B-A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | DeepSeek V4 Flash Base1M | Soofi S 30B-A3B1M | Listed context windows are equal. |
Benchmark Deep Dive
Coding2 benchmarks
Reasoning6 benchmarks
KnowledgeDeepSeek V4 Flash Base wins14 benchmarks
| Benchmark | DeepSeek V4 Flash Base | Soofi S 30B-A3B | Result |
|---|---|---|---|
| AGIEvalSource | 82.6% | 66.9% | DeepSeek V4 Flash Base leads |
| MMLUSource | 88.7% | — | Not comparable |
| MMLU-ReduxSource | 89.4% | — | Not comparable |
| MMLU-ProSource | 68.3% | 51.4% | DeepSeek V4 Flash Base leads |
| MMMLUSource | 88.8% | — | Not comparable |
| C-EvalSource | 92.1% | — | Not comparable |
| CMMLUSource | 90.4% | — | Not comparable |
| MultiLoKoSource | 42.2% | — | Not comparable |
| SimpleQASource | 30.1% | — | Not comparable |
| SuperGPQASource | 46.5% | — | Not comparable |
| FACTS ParametricSource | 33.9% | — | Not comparable |
| TriviaQASource | 82.8% | — | Not comparable |
| GPQASource | — | 43.4% | Not comparable |
| GPQA-DSource | — | 43.4% | Not comparable |
Math3 benchmarks
Multilingual1 benchmarks
| Benchmark | DeepSeek V4 Flash Base | Soofi S 30B-A3B | Result |
|---|---|---|---|
| MGSMSource | 85.7% | — | Not comparable |
Frequently Asked Questions (2)
Which is better, DeepSeek V4 Flash Base or Soofi S 30B-A3B?
Soofi S 30B-A3B is ahead on BenchLM's provisional leaderboard, 45 to 40. The biggest single separator in this matchup is MMLU-Pro, where the scores are 68.3% and 51.4%.
Which is better for knowledge tasks, DeepSeek V4 Flash Base or Soofi S 30B-A3B?
DeepSeek V4 Flash Base has the edge for knowledge tasks in this comparison, averaging 56.5 versus 49.9. Inside this category, MMLU-Pro 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.