Model comparison
DeepSeek V4 Pro vs Gemini 1.5 Flash (May 2024)
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 33.2 on the Noometry Index.
Last verified . 23 shared benchmarks.
DeepSeek
GoogleSummary
- They share 23 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 9 categories and Gemini 1.5 Flash (May 2024) in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.8 to 22.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.6% for DeepSeek V4 Pro and 16.3% for Gemini 1.5 Flash (May 2024).
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 54.3 | 33.2 |
| Released | 2026-04-24 | 2024-05-14 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Gemini 1.5 Flash (May 2024): 34.4 (#236)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| WeirdML | 66.2% | 24.9% |
| LMArena Coding | 1470 | 1261 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| BigCodeBench Instruct | — | 43.5% |
| BigCodeBench Complete | — | 55.1% |
| ALE-Bench | 1,403 | — |
| HumanEval+ | — | 75.6% |
| MBPP+ | — | 67.5% |
Agentic & Tool Use DeepSeek V4 Pro leads
DeepSeek V4 Pro: 32.8 (#58), Gemini 1.5 Flash (May 2024): 26.6 (#102)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| APEX-Agents | 47.3% | — |
| BALROG | — | 14.6% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Gemini 1.5 Flash (May 2024): 21.7 (#215)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1257 |
| DTBench | 93.9% | 53.8% |
| Epoch Capabilities Index | 155.31 | 129.36 |
| ForecastBench | 56.1 | 53.9 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| PIQA | — | 87.5% |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Gemini 1.5 Flash (May 2024): 22.1 (#281)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.6% | 16.3% |
| LMArena Math | 1455 | 1269 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 30.4% |
| MATH Level 5 | — | 61.9% |
| FrontierMath (Feb 2025 set) | — | 0% |
| GSM8K | — | 82.4% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Gemini 1.5 Flash (May 2024): 26.2 (#260)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| GPQA Diamond | 91.7% | 47.3% |
| LMArena Expert | 1464 | 1233 |
| SimpleQA Verified | 52.9% | — |
| MMLU-Pro | — | 67.8% |
| Vectara Hallucination Rate | 8.6% | — |
| GPQA (HELM) | — | 43.7% |
| BoolQ | — | 85.8% |
| MMLU | — | 77.9% |
Multimodal Not comparable
DeepSeek V4 Pro: —, Gemini 1.5 Flash (May 2024): 36.0 (#81)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Vision | — | 1141 |
| Video-MME | — | 70.3% |
| GeoBench | — | 76% |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Gemini 1.5 Flash (May 2024): 42.9 (#189)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Non-English | 1439 | 1278 |
| LMArena Chinese | 1486 | 1295 |
| LMArena French | 1472 | 1258 |
| LMArena German | 1458 | 1262 |
| LMArena Japanese | 1445 | 1252 |
| LMArena Korean | 1447 | 1221 |
| LMArena Russian | 1453 | 1288 |
| LMArena Spanish | 1458 | 1243 |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Gemini 1.5 Flash (May 2024): 66.8 (#205)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1448 | 1258 |
| IFEval | — | 83.1% |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Gemini 1.5 Flash (May 2024): 39.0 (#187)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Longer Query | 1458 | 1284 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Gemini 1.5 Flash (May 2024): 48.7 (#196)
| Benchmark | DeepSeek V4 Pro | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Text | 1451 | 1287 |
| LMArena Creative Writing | 1446 | 1285 |
| LMArena Multi-Turn | 1467 | 1253 |
| EQ-Bench Creative Writing | 1553 | — |
| WildBench | — | 79.2% |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Gemini 1.5 Flash (May 2024)?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 33.2 on the Noometry Index.
Is DeepSeek V4 Pro or Gemini 1.5 Flash (May 2024) better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 34.4 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Gemini 1.5 Flash (May 2024) share?
23 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Gemini 1.5 Flash (May 2024) has 42.