Model comparison
DeepSeek V4 Flash vs Step 3.7 Flash
Head-to-head evidence from 7 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
BenchAlign evidence: DeepSeek V4 Flash estimated; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. DeepSeek V4 Flash and Step 3.7 Flash share 7 comparable benchmark results. 2 of 8 categories are comparable. 16 results are unique to DeepSeek V4 Flash; 23 to Step 3.7 Flash.
Updated July 16, 2026- Shared results
- 7
- DeepSeek V4 Flash only
- 16
- Step 3.7 Flash only
- 23
- Comparable categories
- 2 / 8
Treat this as a split decision. DeepSeek V4 Flash makes more sense if coding is the priority or you want the cheaper token bill; Step 3.7 Flash is the better fit if agentic is the priority or you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 7 shared benchmark results across 3 evidence categories; 2 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 Flash and Step 3.7 Flash finish on the same provisional overall score, so this is less about a single winner and more about where the edge shows up. The provisional headline says tie; the benchmark table is where the real choice happens.
Step 3.7 Flash is also the more expensive model on tokens at $0.20 input / $1.15 output per 1M tokens, versus $0.14 input / $0.28 output per 1M tokens for DeepSeek V4 Flash. That is roughly 4.1x on output cost alone. Step 3.7 Flash is the reasoning model in the pair, while DeepSeek V4 Flash 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. DeepSeek V4 Flash gives you the larger context window at 1M, compared with 256K for Step 3.7 Flash.
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 | Δ | Step 3.7 Flash |
|---|---|---|---|
| Agentic | DeepSeek V4 Flash49.1 | Margin→ 17.3 | Step 3.7 Flash66.4 |
| Coding | DeepSeek V4 Flash64.2 | Margin← 7.9 | Step 3.7 Flash56.3 |
| Knowledge | DeepSeek V4 Flash39.2 | MarginNo overlap | Step 3.7 FlashNot measured |
| Math | DeepSeek V4 Flash40.8 | MarginNo overlap | Step 3.7 FlashNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 49.1%B 59.5%Winner: Step 3.7 FlashΔ 10.4Terminal-Bench 2.0: DeepSeek V4 Flash scored 49.1%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 49.1%B 56.3%Winner: Step 3.7 FlashΔ 7.2SWE-bench Pro: DeepSeek V4 Flash scored 49.1%; Step 3.7 Flash scored 56.3%. Step 3.7 Flash wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | DeepSeek V4 Flash | Step 3.7 Flash | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | DeepSeek V4 Flash$0.14 input / $0.28 output | Step 3.7 Flash$0.2 input / $1.15 output | DeepSeek V4 Flash has the lower combined listed price. |
| Generation speedtokens per second | DeepSeek V4 FlashNot available | Step 3.7 FlashNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | DeepSeek V4 FlashNot available | Step 3.7 FlashNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | DeepSeek V4 Flash1M | Step 3.7 Flash256K | DeepSeek V4 Flash lists the larger context window. |
Benchmark Deep Dive
AgenticStep 3.7 Flash wins13 benchmarks
| Benchmark | DeepSeek V4 Flash | Step 3.7 Flash | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 49.1% | 59.5% | Step 3.7 Flash leads |
| MCP AtlasSource | 64% | — | Not comparable |
| ToolathlonSource | 40.7% | 49.5% | Step 3.7 Flash leads |
| Claw-EvalSource | 57.8% | 67.1% | Step 3.7 Flash leads |
| Gert LabsSource | 54.35% | 51.57% | DeepSeek V4 Flash leads |
| BrowseCompSource | — | 75.8% | Not comparable |
| DeepSearchQASource | — | 92.8% | Not comparable |
| GDPval-AASource | — | 25.9% | Not comparable |
| HLE w/ toolsSource | — | 47.2% | Not comparable |
| AA Agentic IndexSource | — | 21.5% | Not comparable |
| τ²-bench resultsSource | — | 98.5% | Not comparable |
| GDPval-AASource | — | 1017 | Not comparable |
| APEX-Agents-AASource | — | 14.8% | Not comparable |
CodingDeepSeek V4 Flash wins8 benchmarks
| Benchmark | DeepSeek V4 Flash | Step 3.7 Flash | Result |
|---|---|---|---|
| LiveCodeBench Pass@1-COTSource | 55.2% | — | Not comparable |
| SWE-bench VerifiedSource | 73.7% | — | Not comparable |
| SWE-bench ProSource | 49.1% | 56.3% | Step 3.7 Flash leads |
| SWE MultilingualSource | 69.7% | — | Not comparable |
| Terminal-Bench 2.0Source | 49.1% | 59.5% | Step 3.7 Flash leads |
| AA Coding IndexSource | — | 39.6% | Not comparable |
| Terminal-Bench HardSource | — | 35.6% | Not comparable |
| AA-SciCodeSource | — | 40.0% | Not comparable |
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | DeepSeek V4 Flash | Step 3.7 Flash | Result |
|---|---|---|---|
| MMLU-ProSource | 83% | — | Not comparable |
| SimpleQASource | 23.1% | — | Not comparable |
| Chinese-SimpleQASource | 71.5% | — | Not comparable |
| GPQASource | 71.2% | — | Not comparable |
| GPQA-DSource | 71.2% | — | Not comparable |
| HLESource | 8.1% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 30.3% | Not comparable |
| AA-GPQA DiamondSource | — | 80.9% | Not comparable |
| AA-HLESource | — | 19.9% | Not comparable |
| AA-Omniscience IndexSource | — | -37.5% | Not comparable |
| AA-Omniscience AccuracySource | — | 25.4% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 84.4% | Not comparable |
Math4 benchmarks
Multimodal4 benchmarks
Inst. Following1 benchmarks
| Benchmark | DeepSeek V4 Flash | Step 3.7 Flash | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 67.3% | Not comparable |
Frequently Asked Questions (3)
Which is better, DeepSeek V4 Flash or Step 3.7 Flash?
DeepSeek V4 Flash and Step 3.7 Flash are tied on the provisional overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, DeepSeek V4 Flash or Step 3.7 Flash?
DeepSeek V4 Flash has the edge for coding in this comparison, averaging 64.2 versus 56.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, DeepSeek V4 Flash or Step 3.7 Flash?
Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 49.1. Inside this category, Terminal-Bench 2.0 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.