Model comparison
DeepSeek V4 Pro Base vs GPT-4.1 mini
Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: DeepSeek V4 Pro Base unranked (Not scored); GPT-4.1 mini #152 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. DeepSeek V4 Pro Base and GPT-4.1 mini share 1 comparable benchmark result. 1 of 8 categories are comparable. 23 results are unique to DeepSeek V4 Pro Base; 21 to GPT-4.1 mini.
Updated July 23, 2026- Shared results
- 1
- DeepSeek V4 Pro Base only
- 23
- GPT-4.1 mini only
- 21
- Comparable categories
- 1 / 8
Treat this as a split decision. DeepSeek V4 Pro Base makes more sense if knowledge is the priority; GPT-4.1 mini is the better fit if its strengths line up with your actual workload.
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
DeepSeek V4 Pro Base and GPT-4.1 mini finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
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 Pro Base | Δ | GPT-4.1 mini |
|---|---|---|---|
| Knowledge | DeepSeek V4 Pro Base66.4 | Margin← 2.2 | GPT-4.1 mini64.2 |
| Coding | DeepSeek V4 Pro BaseNot measured | MarginNo overlap | GPT-4.1 mini23.6 |
| Reasoning | DeepSeek V4 Pro Base51.5 | MarginNo overlap | GPT-4.1 miniNot measured |
| Math | DeepSeek V4 Pro BaseNot measured | MarginNo overlap | GPT-4.1 mini4.5 |
| Inst. Following | DeepSeek V4 Pro BaseNot measured | MarginNo overlap | GPT-4.1 mini88.5 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | DeepSeek V4 Pro Base | GPT-4.1 mini | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | DeepSeek V4 Pro BaseNot available | GPT-4.1 mini$0.4 input / $1.6 output | A complete price comparison is not available. |
| Generation speedtokens per second | DeepSeek V4 Pro BaseNot available | GPT-4.1 mini80 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | DeepSeek V4 Pro BaseNot available | GPT-4.1 mini0.76 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | DeepSeek V4 Pro Base1M | GPT-4.1 mini1M | Listed context windows are equal. |
Benchmark Deep Dive
Agentic4 benchmarks
Coding5 benchmarks
Reasoning8 benchmarks
| Benchmark | DeepSeek V4 Pro Base | GPT-4.1 mini | Result |
|---|---|---|---|
| BBHSource | 87.5% | — | Not comparable |
| DROPSource | 88.7% | — | Not comparable |
| HellaSwagSource | 88.0% | — | Not comparable |
| WinoGrandeSource | 81.5% | — | Not comparable |
| CLUEWSCSource | 85.2% | — | Not comparable |
| LongBench v2Source | 51.5% | — | Not comparable |
| AA-LCRSource | — | 42.3% | Not comparable |
| CritPtSource | — | 0.0% | Not comparable |
KnowledgeDeepSeek V4 Pro Base wins19 benchmarks
| Benchmark | DeepSeek V4 Pro Base | GPT-4.1 mini | Result |
|---|---|---|---|
| AGIEvalSource | 83.1% | — | Not comparable |
| MMLUSource | 90.1% | 87.5% | DeepSeek V4 Pro Base leads |
| MMLU-ReduxSource | 90.8% | — | Not comparable |
| MMLU-ProSource | 73.5% | — | Not comparable |
| MMMLUSource | 90.3% | — | Not comparable |
| C-EvalSource | 93.1% | — | Not comparable |
| CMMLUSource | 90.8% | — | Not comparable |
| MultiLoKoSource | 51.1% | — | Not comparable |
| SimpleQASource | 55.2% | — | Not comparable |
| SuperGPQASource | 53.9% | — | Not comparable |
| FACTS ParametricSource | 62.6% | — | Not comparable |
| TriviaQASource | 85.6% | — | Not comparable |
| GPQASource | — | 64.2% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 14.8% | Not comparable |
| AA-GPQA DiamondSource | — | 66.4% | Not comparable |
| AA-HLESource | — | 4.6% | Not comparable |
| AA-Omniscience IndexSource | — | -50.1% | Not comparable |
| AA-Omniscience AccuracySource | — | 17.5% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 82.0% | Not comparable |
Math4 benchmarks
Multilingual1 benchmarks
| Benchmark | DeepSeek V4 Pro Base | GPT-4.1 mini | Result |
|---|---|---|---|
| MGSMSource | 84.4% | — | Not comparable |
Multimodal2 benchmarks
Frequently Asked Questions (2)
Which is better, DeepSeek V4 Pro Base or GPT-4.1 mini?
DeepSeek V4 Pro Base and GPT-4.1 mini are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for knowledge tasks, DeepSeek V4 Pro Base or GPT-4.1 mini?
DeepSeek V4 Pro Base has the edge for knowledge tasks in this comparison, averaging 66.4 versus 64.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.