DeepSeek V4 Pro vs Gemini 3.8 Flash
Full profiles: DeepSeek V4 Pro (DeepSeek) and Gemini 3.8 Flash (Google): every benchmark, price and rank.
Updated · Data from 8 sources
As of 16 Nov 2026, Gemini 3.8 Flash is ahead of DeepSeek V4 Pro on quality (60.2 vs 56.0 on the BenchLeader Index), but DeepSeek V4 Pro is 1.5× cheaper at $0.990 vs $1.50 per 1M tokens blended. Gemini 3.8 Flash leads in every category we measure both in. Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.
Key facts (as of 16 Nov 2026)
- DeepSeek V4 Pro scores 56.0 on the BenchLeader Index and Gemini 3.8 Flash scores 60.2 (BenchLeader, 16 Nov 2026).
- DeepSeek V4 Pro costs $0.990 per 1M tokens blended (list price, 16 Nov 2026).
- Gemini 3.8 Flash costs $1.50 per 1M tokens blended until 31 Dec 2026, then $3.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
- Gemini 3.8 Flash streams ~2× faster than DeepSeek V4 Pro (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 21 benchmarks both models have, Gemini 3.8 Flash leads 19 (BenchLeader, 16 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Either | 52 vs 52 category score; FrontierCode 2.0 (AA) 16.7% vs 16.5% | Either |
| Reasoning | Gemini 3.8 Flash | 59 vs 56 category score; HLE-Diamond (AA) 29.1% vs 20.5% | Medium |
| Knowledge | Gemini 3.8 Flash | 58 vs 41 category score; AA-Omniscience v1.1 23.7 vs -6.5 | High |
| Long documents | Gemini 3.8 Flash | 67 vs 64 category score; AA-LCR v1.1 84.0% vs 79.3% | Medium |
| Chat quality (human preference) | – | Only DeepSeek V4 Pro has an Arena rating (65 category score) | Not comparable |
| Lowest cost | Gemini 3.8 Flash (until 31 Dec 2026) | $1.50 vs $1.98 per 1M blended; agentic coding session $0.060 vs $0.095; from 1 Jan 2027: $3.00 vs $1.98 | – |
| Fastest first answer | Gemini 3.8 Flash | 14.8 s (Gemini 3.8 Flash (medium)) vs 42.8 s (DeepSeek V4 Pro (high)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Gemini 3.8 Flash (medium) leads on quality: 60.2 vs 56.0.
- Gemini 3.8 Flash (medium) is stronger in coding, knowledge, long context, reasoning.
- DeepSeek V4 Pro (high) is 1.5× cheaper ($0.990 vs $1.50 per 1M blended) until 31 Dec 2026, then $1.98 vs $3.00 from 1 Jan 2027.
- Gemini 3.8 Flash (medium) streams 1.4× faster (116 vs 80 tokens per second).
At a glance
| Spec | DeepSeek V4 Pro | Gemini 3.8 Flash |
|---|---|---|
| Developer | DeepSeek | |
| Released | 13 Aug 2026 | 2 Sep 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | DeepSeek V4 Pro (high) | Gemini 3.8 Flash (medium) |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $1.32 / $3.96 / $0.022 | $0.750 / $3.75 / $0.075 |
| Announced price change | None announced | $1.50 / $7.50 from 1 Jan 2027 |
Limits, availability and announced prices from the vendors' own pages: ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | DeepSeek V4 Pro (high) | Gemini 3.8 Flash (medium) | Leader |
|---|---|---|---|
| Reasoning | 55.6 | 58.7 | Gemini 3.8 Flash |
| Coding | 51.5 | 51.6 | level |
| Agents & tools | – | 75.0 | not comparable |
| Maths | 64.5 | – | not comparable |
| Knowledge | 41.2 | 57.7 | Gemini 3.8 Flash |
| Human preference | 65.0 | – | not comparable |
| Multimodal | – | 66.7 | not comparable |
| Long context | 64.3 | 66.7 | Gemini 3.8 Flash |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Multimodal, Human preference.
Where sources disagree
Across the 21 benchmarks both have, DeepSeek V4 Pro leads 2, Gemini 3.8 Flash leads 19. Every overall index that rates both puts Gemini 3.8 Flash ahead.
| Overall index | DeepSeek V4 Pro (high) | Gemini 3.8 Flash (medium) | Leader |
|---|---|---|---|
| BenchLeader Index | 56.0 | 60.2 | Gemini 3.8 Flash |
| AA Intelligence Index v5.0.1 | 20.8 | 30.1 | Gemini 3.8 Flash |
| Vals Index | 53.0† | 56.0 | Gemini 3.8 Flash |
| Arena Text | 1464 | 1497† | Gemini 3.8 Flash |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | DeepSeek V4 Pro (high) | Gemini 3.8 Flash (medium) |
|---|---|---|
| Blended price per 1M tokens, until 31 Dec 2026 | $1.98 | $1.50 |
| Input / output per 1M | $1.32 / $3.96 | $0.750 / $3.75 |
| Blended price per 1M from 1 Jan 2027 | $1.98 | $3.00 |
| Input / output per 1M from 1 Jan 2027 | $1.32 / $3.96 | $1.50 / $7.50 |
| Cached input per 1M | $0.022 | $0.075 |
| Price per task: chat reply | $0.0017 | $0.0014 |
| Price per task: summarize a 30-page report | $0.018 | $0.011 |
| Price per task: code edit | $0.014 | $0.010 |
| Price per task: agentic coding session | $0.095 | $0.060 |
| Price per task: structured extraction | $0.0034 | $0.0023 |
| Agentic coding session, input mostly cached | $0.037 | $0.030 |
| Cost per benchmark task (AA Index) | $0.849 | $6.26 |
| Output tokens per task (AA Index) | 70k | 82k |
| Of which reasoning | 45k | 47k |
| Time per task (AA Index) | 15 min | 12 min |
| Output speed | 80 tok/s | 116 tok/s |
| Time to first answer | 42.8 s | 14.8 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 41.8 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.849 on DeepSeek V4 Pro (high) and $6.26 on Gemini 3.8 Flash (medium), and Gemini 3.8 Flash (medium) wrote 1.2× as many output tokens for the same work.
Each model is compared at its best-ranked reasoning-effort setting. DeepSeek V4 Pro (high) scores 56.0 and takes 43 s to its first answer token; DeepSeek V4 Pro (max) scores 54.7 in 47 s, DeepSeek V4 Pro scores 53.0 in 1 s. Gemini 3.8 Flash (medium) scores 60.2 and takes 15 s to its first answer token; Gemini 3.8 Flash (high) scores 59.4 in 20 s, Gemini 3.8 Flash scores 56.4 in 2 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
191 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | DeepSeek V4 Pro (high) | Gemini 3.8 Flash (medium) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 56.0 | 60.2 |
| Coding score | BenchLeader | 51.5 | 51.6 |
| Human preference score | BenchLeader | 65.0 | – |
| Knowledge score | BenchLeader | 41.2 | 57.7 |
| Long context score | BenchLeader | 64.3 | 66.7 |
| Maths score | BenchLeader | 64.5 | – |
| Reasoning score | BenchLeader | 55.6 | 58.7 |
| Agents & tools score | BenchLeader | – | 75.0 |
| Multimodal score | BenchLeader | – | 66.7 |
| Blended price $/M | BenchLeader | $1.98 | $1.50 |
| Output speed | BenchLeader | 80 tok/s | 116 tok/s |
| Time to first answer | BenchLeader | 42.8 s | 14.8 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 90.9% | 95.4%† |
| Humanity's Last Exam | Scale AI / CAIS | – | 44.5%† |
| SimpleBench | SimpleBench | – | 82.4%† |
| Arena Hard Prompts | Arena (LMArena) | 1482 | 1518† |
| LiveBench 2.0 Reasoning | LiveBench | – | 89.3%† |
| LiveBench 1.0 Reasoning | LiveBench | 85.8%† | 89.3%† |
| GPQA Diamond (AA) | Artificial Analysis | 92.8%† | 93.5% |
| Humanity's Last Exam (AA) | Artificial Analysis | 41.5% | 42.1% |
| HLE-Diamond (AA) | Artificial Analysis | 20.5% | 29.1% |
| GPQA Diamond (Vals) | Vals AI | 92.4%† | 94.4%† |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 53.5%† | – |
| ARC-AGI-1 | ARC Prize | 87.2% | 97.5% |
| ARC-AGI-2 | ARC Prize | 59.7% | 82.9% |
| ARC-AGI-3 | ARC Prize | – | 24.2% |
| CritPt | Artificial Analysis | 18.6% | 12.3% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 28.5% | 45.0% |
| MysteryMechanism | Vals AI | – | 36.5%† |
| HLE-Diamond (Scale) | Scale AI SEAL | 13.4%† | 34.3%† |
| Arena Expert | Arena (LMArena) | 1481 | 1527† |
| Chess Puzzles | Epoch AI Benchmarking Hub | 16.0% | 58.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 43.0%† | 47.0%† |
| CL-bench Life | Epoch AI Benchmarking Hub | 13.5% | – |
| LMCA | Epoch AI Benchmarking Hub | 45.5%† | 52.9% |
| DTBench | Epoch AI Benchmarking Hub | 93.9%† | 94.9% |
| ForecastBench | ForecastBench | 60.7%† | – |
Show all 191 benchmarks
| Metric | Publisher | DeepSeek V4 Pro (high) | Gemini 3.8 Flash (medium) |
|---|---|---|---|
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 77.6%† | – |
| SciCode | SciCode | 46.4% | 55.1% |
| WeirdML | WeirdML | 46.5% | 84.8%† |
| FrontierCode | Cognition | 28.6% | 41.2% |
| Arena Coding | Arena (LMArena) | 1503 | 1531† |
| Arena WebDev | Arena (LMArena) | 1581 | 1584† |
| LiveBench 2.0 Coding | LiveBench | – | 73.3%† |
| LiveBench 1.0 Coding | LiveBench | 77.2%† | 72.5%† |
| SciCode (AA) | Artificial Analysis | 51.7% | 55.1% |
| LiveCodeBench | Vals AI | 87.5%† | 89.5%† |
| IOI | Vals AI | 51.6%† | 56.9%† |
| SWE-bench (Vals) | Vals AI | 96.4%† | 80.0%† |
| Code Migration | Vals AI | 41.5%† | 36.5%† |
| Code Migration v1.1 | Vals AI | 52.0%† | 38.6%† |
| ProgramBench | Vals AI | 0.0%† | 1.0%† |
| SWE-bench Multimodal | Vals AI | – | 40.8%† |
| Vibe Code Bench 1-100 | Vals AI | 17.5%† | 18.8%† |
| Vibe Code Bench v1.1 | Vals AI | 82.3%† | 78.7%† |
| SWE Atlas v1.0: Codebase QnA | Scale AI SEAL | 27.1%† | 47.0%† |
| SWE Atlas v1.0: Refactoring | Scale AI SEAL | – | 44.8%† |
| SWE Atlas v1.0: Test Writing | Scale AI SEAL | 27.1%† | 53.7%† |
| SWE Atlas v1.1 | Scale AI SEAL | – | 57.3%† |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 45.2%† |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 71.1%† |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 55.7%† |
| SWE-Bench Pro V2 | Scale AI SEAL | – | 94.9%† |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | – | 58.8%† |
| MirrorCode | Epoch AI Benchmarking Hub | 33.3%† | 38.9%† |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 40.0% | 76.9%† |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 71.0% |
| CursorBench | Cursor | – | 37.3% |
| ALE-Bench | Epoch AI Benchmarking Hub | 1006.1 | 1269.7† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 19.6%† |
| WeirdML v3 | WeirdML | – | 7.4%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 6.1% | 19.7% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 78.7%† | 83.9% |
| Startrise Frontend | Startrise | 62.7%† | 64.6%† |
| GameBench 2 Overall | DuelLab GameBench 2 | 41.9† | 59.0† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 45.1 | 59.7 |
| Design Arena Website | Design Arena | 1227† | 1291† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 38.8%† | 37.1% |
| FrontierCode 2.0 (AA) | Artificial Analysis | 16.7% | 16.5% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 6.7%† | 18.2%† |
| Remote Labor Index | Scale AI / CAIS | – | 5.8%† |
| APEX-Agents | Mercor | 47.3%† | 64.3%† |
| Arena Agent | Arena (LMArena) | – | 2.3† |
| LiveBench Long Agentic | LiveBench | – | 16.5%† |
| LiveBench Browser | LiveBench | – | 45.1%† |
| LiveBench Agentic Coding | LiveBench | 55.0%† | 54.2%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | 50.2%† | 81.3%† |
| HiL-Bench | Scale AI SEAL | 38.5%† | 41.5%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 47.5%† | 46.1% |
| GDPval-AA v2.1 | Artificial Analysis | 1336 | 1432 |
| τ³-Banking (AA) | Artificial Analysis | 39.6%† | 45.8% |
| ITBench SRE (AA) | Artificial Analysis | – | 52.5%† |
| Analyst Agent (AA) | Artificial Analysis | – | 46.3%† |
| CUA-bench | Vals AI | – | 4.2%† |
| CyberBench | Vals AI | 72.9%† | 43.8%† |
| Finance Agent v2 | Vals AI | 50.4%† | 61.4%† |
| Finance Agent v2.1 | Vals AI | 57.1%† | 65.8%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 10.8%† | 12.1%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 7.5%† | 10.0%† |
| Legal Research Bench | Vals AI | 40.9%† | 38.9%† |
| SkillsBench | Vals AI | 53.8%† | 58.0%† |
| SREBench | Vals AI | 1.9%† | 11.1%† |
| Tax Agent Bench | Vals AI | 26.8%† | 32.1%† |
| Terminal-Bench 2.0 (Vals) | Vals AI | 56.2%† | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 14.1%† | 19.7%† |
| Terminal-Bench Science | Vals AI | 4.3%† | 8.6%† |
| Time Horizon Index: KSP | Vals AI | – | 18.8%† |
| Arena Agent Task Completion | Arena (LMArena) | – | 1.3† |
| Vending-Bench 2 | Andon Labs | 3284.5† | 5093.8† |
| AutomationBench | Artificial Analysis | 46.2% | 60.9% |
| GDP.pdf (AA) | Artificial Analysis | 10.4% | 22.8% |
| Harvey LAB-AA v1.1 | Harvey | – | 0.0%† |
| EnterpriseOps-Gym | Artificial Analysis | 49.6%† | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1148 | 1183 |
| Design Arena Agentic | Design Arena | 927† | 1225† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 1.9% | 10.5% |
| CWE-Bench (AA) | Artificial Analysis | – | 52.5%† |
| DeepSec-Bench (AA) | Artificial Analysis | – | 14.5%† |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 8.4%† |
| MKA (AA) | Artificial Analysis | – | 35.3%† |
| FACTS Search | – | 80.4%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 64.6%† | 68.4%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 26.8%† | 21.9%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 95.6% | 98.9%† |
| ProofBench | Vals AI | 50.0%† | 48.0%† |
| LiveBench Mathematics | LiveBench | 95.1%† | 91.6%† |
| AIME 2026 | MathArena | 96.7%† | – |
| HMMT February 2026 | MathArena | 93.9%† | – |
| USAMO 2026 | MathArena | 60.7%† | – |
| MathArena Apex | MathArena | 28.1%† | – |
| Arena Maths | Arena (LMArena) | 1465 | 1519† |
| FrontierMath Erdős | Epoch AI Benchmarking Hub | – | 0.0%† |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 52.9%† | 69.7%† |
| LiveBench 2.0 Data Analysis | LiveBench | – | 54.0%† |
| LiveBench Research | LiveBench | – | 79.4%† |
| LiveBench 1.0 Data Analysis | LiveBench | 79.2%† | 54.0%† |
| AA-Omniscience v1.1 | Artificial Analysis | -6.5 | 23.7 |
| MMLU-Pro | Vals AI | 87.3%† | 90.2%† |
| LegalBench | Vals AI | 82.4%† | 87.0%† |
| CorpFin | Vals AI | 65.4%† | – |
| TaxEval | Vals AI | 73.1%† | 74.5%† |
| PRBench Finance | Scale AI SEAL | – | 49.5%† |
| PRBench Legal | Scale AI SEAL | – | 48.9%† |
| BioMysteryBench | Vals AI | – | 62.2%† |
| CaseLaw v2 | Vals AI | 59.4%† | – |
| Excel Modeling Benchmark | Vals AI | 52.8%† | 72.2%† |
| Excel Modeling Benchmark v1.1 | Vals AI | 65.1%† | 72.9%† |
| MedCode | Vals AI | 42.5%† | 48.1%† |
| MedScribe | Vals AI | 80.2%† | 84.5%† |
| Public Benefits Bench v1.1 | Vals AI | 62.9%† | 65.3%† |
| Access to Justice Benchmark | Vals AI | – | 67.1%† |
| Financial Coaching Bench | Vals AI | – | 66.3%† |
| Immigration Bench | Vals AI | 61.7%† | 63.4%† |
| DrugDiscoveryBench | Scale AI SEAL | 31.7%† | – |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 23.4% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 45.1% | 49.6% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 5.9% | 48.5% |
| HealthBench Professional (AA) | OpenAI | – | 51.7%† |
| FACTS Parametric | – | 78.7%† | |
| Instruction following | |||
| LiveBench Language | LiveBench | 82.1%† | 87.8%† |
| LiveBench Instruction Following | LiveBench | 67.7%† | 81.4%† |
| Arena Instruction Following | Arena (LMArena) | 1461 | 1492† |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1464 | 1497† |
| EQ-Bench 4 | EQ-Bench | 1156† | – |
| EQ-Bench Creative Writing v3 | EQ-Bench | 1553† | 1744† |
| Arena Creative Writing | Arena (LMArena) | 1444 | 1488† |
| Arena Multi-turn | Arena (LMArena) | 1469 | 1505† |
| Arena Longer Queries | Arena (LMArena) | 1474 | 1511† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1317† |
| LiveBench Design | LiveBench | – | 69.7%† |
| MMMU-Pro | Artificial Analysis | – | 84.2% |
| MMMU-Pro (Vals) | Vals AI | – | 89.1%† |
| MortgageTax | Vals AI | – | 65.3%† |
| SAGE | Vals AI | – | 88.2%† |
| AudioMC | Scale AI SEAL | – | 60.4%† |
| AudioMC (text output) | Scale AI SEAL | – | 60.4%† |
| Humanity's Sixth Sense | Scale AI SEAL | – | 41.6%† |
| GeoBench | GeoBench | – | 86.0%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 38.6%† |
| Furniture Assembly | Epoch AI Benchmarking Hub | – | 31.7%† |
| VIALS-AA | Handshake AI | – | 41.0%† |
| Code2Video-AA | Artificial Analysis | – | 899† |
| AA-3D | Artificial Analysis | – | 974† |
| FACTS Multimodal | – | 57.6%† | |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 79.3% | 84.0% |
| Arena Document | Arena (LMArena) | – | 1469† |
| MLCR | Artificial Analysis | – | 12.8% |
| FACTS Grounding | – | 68.2%† | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 155.9† | 158.8† |
| LiveBench 2.0 | LiveBench | – | 57.3%† |
| LiveBench 1.0 | LiveBench | 77.4%† | 75.8%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 20.8 | 30.1 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 36† | 39.8 |
| AA Progress Index v1 | Artificial Analysis | 311.5† | 319.1 |
| Vals Index | Vals AI | 53.0† | 56.0† |
| Vals Finance Index | Vals AI | 52.9%† | 60.5%† |
| Vals RSI Index | Vals AI | – | 19.9%† |
| Vals Science Index | Vals AI | – | 35.8%† |
| Vals Router Index | Vals AI | 53.0%† | 56.0%† |
| Vals Legal Index | Vals AI | 69.0%† | 69.8%† |
| AA Cyber Index | Artificial Analysis | – | 25.1† |
| Safety & honesty | |||
| DistressBench | Scale AI SEAL | – | 70.7%† |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 44.4 | – |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Gemini 3.8 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
- Gemini 3.8 Flash (medium): 1 score revision.
- DeepSeek V4 Pro (high): BenchLeader Index 59.1 → 56.0.
- DeepSeek V4 Pro (high): 17 new results (AA Intelligence Index v5.0.1, Humanity's Last Exam (AA), HLE-Diamond (AA)…); input price moved from $0.66/M to $1.32/M (100% up); output price moved from $1.98/M to $3.96/M (100% up).
- DeepSeek V4 Pro (high): BenchLeader Index 57.5 → 59.1.
- DeepSeek V4 Pro (high): 1 score revision.
- DeepSeek V4 Pro (high): 1 score revision.
- Gemini 3.8 Flash (medium): 2 score revisions.
- Gemini 3.8 Flash (medium): 1 score revision.
- Gemini 3.8 Flash (medium): 1 new result (AA-Briefcase v1.1).
Related comparisons
- DeepSeek V4 Pro vs Claude Fable 5.2
- DeepSeek V4 Pro vs Claude Opus 5.5
- Gemini 3.8 Flash vs Gemini 4 Carbon
- DeepSeek V4 Pro vs Gemini 3.7 Flash
- DeepSeek V4 Pro vs Claude Fable 5.1
- DeepSeek V4 Pro vs GPT-6.1 Sol
- DeepSeek V4 Pro vs Gemini 4 Argon
- DeepSeek V4 Pro vs GPT-5.6 Sol
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
DeepSeek V4 Pro vs Gemini 3.8 Flash: questions
- Is Gemini 3.8 Flash better than DeepSeek V4 Pro?
- Gemini 3.8 Flash (medium) leads on quality: 60.2 vs 56.0. The BenchLeader Index combines every independent quality benchmark; Gemini 3.8 Flash (medium) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
- DeepSeek V4 Pro vs Gemini 3.8 Flash: which is cheaper, and will that change?
- DeepSeek V4 Pro is cheaper today: $0.990 against $1.50 per million tokens, blended at three input tokens per output token. Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.
- Is DeepSeek V4 Pro or Gemini 3.8 Flash better for coding?
- They are level in coding (52 vs 52 on the category index). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 16.7% for DeepSeek V4 Pro against 16.5% for Gemini 3.8 Flash.
- Which is faster, DeepSeek V4 Pro or Gemini 3.8 Flash?
- Gemini 3.8 Flash streams ~2× faster (116 vs 80 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Gemini 3.8 Flash scores higher on long-context benchmarks (67 vs 64). Both accept 1,048,576 tokens of context.
More questions (3)
- Which has lower latency?
- Gemini 3.8 Flash answers first: 14.8 s against 42.8 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on DeepSeek V4 Pro vs Gemini 3.8 Flash?
- Across the 21 benchmarks both have, DeepSeek V4 Pro leads 2, Gemini 3.8 Flash leads 19. Every overall index that rates both puts Gemini 3.8 Flash ahead.
- When was Gemini 3.8 Flash released?
- Gemini 3.8 Flash was released on 2 Sep 2026.