Model comparison
DeepSeek V3.1 (Reasoning) vs DeepSeek V4 Flash (High)
Head-to-head evidence from 12 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: DeepSeek V3.1 (Reasoning) #97 (Supported); DeepSeek V4 Flash (High) #92 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. DeepSeek V3.1 (Reasoning) and DeepSeek V4 Flash (High) share 12 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to DeepSeek V3.1 (Reasoning); 26 to DeepSeek V4 Flash (High).
Updated July 23, 2026- Shared results
- 12
- DeepSeek V3.1 (Reasoning) only
- 0
- DeepSeek V4 Flash (High) only
- 26
- Comparable categories
- 0 / 8
Benchmark data for DeepSeek V3.1 (Reasoning) and DeepSeek V4 Flash (High) is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
DeepSeek V4 Flash (High) is priced at $0.14 input / $0.28 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for DeepSeek V3.1 (Reasoning). DeepSeek V4 Flash (High) has the larger context window at 1M, compared with 128K for DeepSeek V3.1 (Reasoning).
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 V3.1 (Reasoning) | Δ | DeepSeek V4 Flash (High) |
|---|---|---|---|
| Agentic | DeepSeek V3.1 (Reasoning)Not measured | MarginNo overlap | DeepSeek V4 Flash (High)55.3 |
| Coding | DeepSeek V3.1 (Reasoning)Not measured | MarginNo overlap | DeepSeek V4 Flash (High)68.5 |
| Knowledge | DeepSeek V3.1 (Reasoning)Not measured | MarginNo overlap | DeepSeek V4 Flash (High)52.1 |
| Math | DeepSeek V3.1 (Reasoning)Not measured | MarginNo overlap | DeepSeek V4 Flash (High)91.9 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | DeepSeek V3.1 (Reasoning) | DeepSeek V4 Flash (High) | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | DeepSeek V3.1 (Reasoning)$0 input / $0 output | DeepSeek V4 Flash (High)$0.14 input / $0.28 output | DeepSeek V3.1 (Reasoning) has the lower combined listed price. |
| Generation speedtokens per second | DeepSeek V3.1 (Reasoning)Not available | DeepSeek V4 Flash (High)Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | DeepSeek V3.1 (Reasoning)Not available | DeepSeek V4 Flash (High)Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | DeepSeek V3.1 (Reasoning)128K | DeepSeek V4 Flash (High)1M | DeepSeek V4 Flash (High) lists the larger context window. |
Benchmark Deep Dive
Agentic9 benchmarks
| Benchmark | DeepSeek V3.1 (Reasoning) | DeepSeek V4 Flash (High) | Result |
|---|---|---|---|
| τ²-bench resultsSource | 37.4% | 95.6% | DeepSeek V4 Flash (High) leads |
| Terminal-Bench 2.0Source | — | 56.6% | Not comparable |
| BrowseCompSource | — | 53.5% | Not comparable |
| HLE w/ toolsSource | — | 40.3% | Not comparable |
| MCP AtlasSource | — | 67.4% | Not comparable |
| ToolathlonSource | — | 43.5% | Not comparable |
| AA Agentic IndexSource | — | 28.2% | Not comparable |
| GDPval-AASource | — | 32.4% | Not comparable |
| GDPval-AASource | — | 1147 | Not comparable |
Coding7 benchmarks
| Benchmark | DeepSeek V3.1 (Reasoning) | DeepSeek V4 Flash (High) | Result |
|---|---|---|---|
| AA-SciCodeSource | 39.1% | 42.0% | DeepSeek V4 Flash (High) leads |
| CodeforcesSource | — | 2816.0 | Not comparable |
| SWE-bench VerifiedSource | — | 78.6% | Not comparable |
| SWE-bench ProSource | — | 52.3% | Not comparable |
| SWE MultilingualSource | — | 70.2% | Not comparable |
| Terminal-Bench 2.0Source | — | 56.6% | Not comparable |
| AA Coding IndexSource | — | 52.0% | Not comparable |
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | DeepSeek V3.1 (Reasoning) | DeepSeek V4 Flash (High) | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 20.7% | 37.5% | DeepSeek V4 Flash (High) leads |
| AA-GPQA DiamondSource | 77.9% | 86.7% | DeepSeek V4 Flash (High) leads |
| AA-HLESource | 13.0% | 27.8% | DeepSeek V4 Flash (High) leads |
| AA-Omniscience IndexSource | -28.4% | -22.3% | DeepSeek V4 Flash (High) leads |
| AA-Omniscience AccuracySource | 28.8% | 35.5% | DeepSeek V4 Flash (High) leads |
| AA-Omniscience Hallucination RateSource | 80.3% | 89.7% | DeepSeek V3.1 (Reasoning) leads |
| MMLU-ProSource | — | 86.4% | Not comparable |
| SimpleQASource | — | 28.9% | Not comparable |
| Chinese-SimpleQASource | — | 73.2% | Not comparable |
| GPQASource | — | 87.4% | Not comparable |
| GPQA-DSource | — | 87.4% | Not comparable |
| HLESource | — | 29.4% | Not comparable |
Math4 benchmarks
Multimodal1 benchmarks
| Benchmark | DeepSeek V3.1 (Reasoning) | DeepSeek V4 Flash (High) | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1152 | 1238 | DeepSeek V4 Flash (High) leads |
Inst. Following1 benchmarks
| Benchmark | DeepSeek V3.1 (Reasoning) | DeepSeek V4 Flash (High) | Result |
|---|---|---|---|
| AA-IFBenchSource | 41.5% | 73.5% | DeepSeek V4 Flash (High) leads |
Frequently Asked Questions (3)
Can I compare DeepSeek V3.1 (Reasoning) and DeepSeek V4 Flash (High) on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for DeepSeek V3.1 (Reasoning) and DeepSeek V4 Flash (High) today?
DeepSeek V3.1 (Reasoning): $0.00 input / $0.00 output per 1M tokens DeepSeek V4 Flash (High): $0.14 input / $0.28 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
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.